# Import python libraries required for this report
import pandas as pd
import json
from time import sleep
from datetime import datetime
import numpy as np
import requests                
from bs4 import BeautifulSoup  
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import matplotlib
import seaborn as sns
from pylab import rcParams
%matplotlib inline
matplotlib.style.use('ggplot')
import time

#The first dataset: GDP contribution

#URL:https://rep.infometrics.co.nz/new-zealand/economy/growth-contributors
#ANZSIC Level 1 industries' contribution to growth, 2022-2023

# Define URL for GDP data retrieval
url1 = 'https://production.infometrics.co.nz/api/rep/data/?series=GDP&year=2022&year=2023&breakdown=GROWTH&area_id=new-zealand&industry_type_code=L1&industry_type_code=TOTAL'

# Send GET request to retrieve GDP data
response1 = requests.get(url1)
data1 = response1.json()  

# Expanding nested data with json_normalize
industryGDP_series = pd.json_normalize(data1, 'series', errors='ignore')

industryGDP_values = pd.json_normalize(data1, record_path=['series', 'values'], 
                              meta=['key', ['industry_types', 'industry_type_code'], ['industry_types', 'name']],
                              errors='ignore')

industryGDP_values.head()

# Select the specified column and create a copy
industryGDP = industryGDP_values[['industry_short', 'value_base', 'value_focus']].copy()

industryGDP.head()

# Rename Columns
industryGDP.rename(columns={
   'industry_short': 'Industry',
   'value_base': 'GDP_2022(M)',
   'value_focus': 'GDP_2023(M)',
   }, inplace=True)

# Setting the graph size
plt.figure(figsize=(10, 4))

# Use index as the x-axis coordinate
index_labels = range(len(industryGDP))

# Plot histograms of both variables separately
plt.subplot(1, 2, 1)  
plt.bar(index_labels, industryGDP['GDP_2022(M)'], color='blue', alpha=0.7)
plt.title('GDP_Contribution_2022')
plt.xlabel('Index')
plt.ylabel('Value')
plt.xticks(index_labels)  

plt.subplot(1, 2, 2)
plt.bar(index_labels, industryGDP['GDP_2023(M)'], color='green', alpha=0.7)
plt.title('GDP_Contribution_2023')
plt.xlabel('Index')
plt.ylabel('Value')
plt.xticks(index_labels)  

plt.tight_layout()


plt.show()

industryGDP = industryGDP.drop(0)
industryGDP.head()

#The second dataset: Employment contribution

#Contribution to employment by industry: 2023 vs. 2022
#https://rep.infometrics.co.nz/new-zealand/employment/growth-contributors
url2 = 'https://production.infometrics.co.nz/api/rep/data/?series=EMP_FILLED&year=2022&year=2023&breakdown=GROWTH&area_id=new-zealand&industry_type_code=L1'

response2 = requests.get(url2)
data2 = response2.json()  

# Expanding nested data with json_normalize
industryEmployment_series = pd.json_normalize(data2, 'series', errors='ignore')

industryEmployment_values = pd.json_normalize(data2, record_path=['series', 'values'], 
                              meta=['key', ['industry_types', 'industry_type_code'], ['industry_types', 'name']],
                              errors='ignore')




industryEmployment_values.head()

# Select the specified column and create a copy
industryEmployment = industryEmployment_values[['industry_short', 'value_base', 'value_focus']].copy()

industryEmployment.rename(columns={
   'industry_short': 'Industry',
   'value_base': 'Employment_2022',
   'value_focus': 'Employment_2023',
   }, inplace=True)

# Setting the graph size
plt.figure(figsize=(10, 4))

# Use index as the x-axis coordinate
index_labels = range(len(industryEmployment))

# Plot histograms of both variables separately
plt.subplot(1, 2, 1)  
plt.bar(index_labels, industryEmployment['Employment_2022'], color='blue', alpha=0.7)
plt.title('GDP_Contribution_2022')
plt.xlabel('Index')
plt.ylabel('Value')
plt.xticks(index_labels)  

plt.subplot(1, 2, 2)
plt.bar(index_labels, industryEmployment['Employment_2023'], color='green', alpha=0.7)
plt.title('GDP_Contribution_2023')
plt.xlabel('Index')
plt.ylabel('Value')
plt.xticks(index_labels)  

plt.tight_layout()


plt.show()

print(industryEmployment.iloc[1]['Industry'])
print(industryEmployment.iloc[3]['Industry'])

mining
electricity, gas, water, waste

# Merge two DataFrames based on Industry columns
merged_industrycontribution = pd.merge(industryEmployment, industryGDP, on='Industry')

merged_industrycontribution.head()

color1 = 'lightblue'
color2 = 'salmon'

fig, axes = plt.subplots(nrows=1, ncols=2, figsize=(16, 8))  

# the first figure：GDP Contribution by Industry for 2022 and 2023
bar_height = 0.35
opacity = 0.8

index1 = range(len(merged_industrycontribution['Industry']))

bar1_1 = axes[0].barh(index1, merged_industrycontribution['GDP_2022(M)'], bar_height, alpha=opacity, color=color1, label='GDP_2022(M)')
bar1_2 = axes[0].barh([p + bar_height for p in index1], merged_industrycontribution['GDP_2023(M)'], bar_height, alpha=opacity, color=color2, label='GDP_2023(M)')

axes[0].set_ylabel('')
axes[0].set_xlabel('GDP Contribution (Millions)')
axes[0].set_title('GDP Contribution by Industry for 2022 and 2023')
axes[0].set_yticks([p + bar_height / 2 for p in index1])
axes[0].set_yticklabels(merged_industrycontribution['Industry'])
axes[0].legend()

# the second：Ely Contribution by Industry for 2022 and 2023
index2 = range(len(merged_industrycontribution['Industry']))

bar2_1 = axes[1].barh(index2, merged_industrycontribution['Employment_2022'], bar_height, alpha=opacity, color=color1, label='Employment_2022')
bar2_2 = axes[1].barh([p + bar_height for p in index2], merged_industrycontribution['Employment_2023'], bar_height, alpha=opacity, color=color2, label='Employment_2023')

axes[1].set_ylabel('')
axes[1].set_xlabel('Employment Contribution (Millions)')
axes[1].set_title('Employment Contribution by Industry for 2022 and 2023')
axes[1].set_yticks([p + bar_height / 2 for p in index2])
axes[1].set_yticklabels(merged_industrycontribution['Industry'])
axes[1].legend()

plt.tight_layout()
plt.show()

# URL
base_url = "https://www.careers.govt.nz/searchresults?tab=jobs"
total_pages = 42  # Total pages

data = []

for page in range(total_pages):
    # Calculate the start position of each page
    start_index = page * 10
    
    # Building URLs for paging
    url = f"{base_url}&start={start_index}"
    
    # Request page
    response = requests.get(url)
    html_content = response.text
    
    # Parsing HTML
    soup = BeautifulSoup(html_content, 'html.parser')
    
    # Iterate over all article tags
    for article in soup.find_all('article', class_='careers-card job'):
        title = article.find('h3', class_='title').text.strip()
        sub_title = article.find('p', class_='sub-title').text.strip()
        description = article.find('div', class_='description').p.text.strip()
        job_opportunities = article.find('dl', class_='job-opportunities').dd.text.strip()
        training_required = article.find('dl', class_='training').dd.text.strip() if article.find('dl', class_='training') else 'N/A'
        vocations = [li['title'] for li in article.find_all('li')]
        earnings = [span.text.strip() for span in article.find_all('span', class_='amount')]

        # Organising data
        data.append({
            'Title': title,
            'Sub Title': sub_title,
            'Description': description,
            'Job Opportunities': job_opportunities,
            'Training Required': training_required,
            'Vocations': ", ".join(vocations),
            'Earnings': ", ".join(earnings)
        })
    
    # 1 second delay after each cycle
    time.sleep(1)

# Create a DataFrame
df_jobprofiles = pd.DataFrame(data)

df_jobprofiles.head()

# descriptive statistics of the dataset
df_jobprofiles.describe()

# Rename Columns
df_jobprofiles.rename(columns={
   'Vocations': 'Industry',
   'Title': 'Occupation',
   }, inplace=True)

jobprofiles = df_jobprofiles[['Occupation', 'Job Opportunities','Industry']].copy()

jobprofiles.head()

# Split multiple occupational categories in the ‘Vocations’ column and then flatten the multi-category structure.
jobprofiles['Industry'] = jobprofiles['Industry'].str.split(', ')
jobprofiles = jobprofiles.explode('Industry').reset_index(drop=True)

# Creating a Crosstab with crosstab
summary_table = pd.crosstab(jobprofiles['Industry'], jobprofiles['Job Opportunities'])

# Calculate the total number of ratings for each job opportunity
total_job_opportunities = summary_table.sum()

summary_table

# import data
file_path = "../AAA/datasets/jobs-online-all.xlsx"

 # specify the first two rows as a multilevel column index
df_jobonline_all = pd.read_excel(file_path, header=[0, 1]) 

df_jobonline_all.head()

#View all column names
columns = df_jobonline_all.columns.tolist()

print("Columns in the dataset:", columns)

Columns in the dataset: [('Date', 'Unnamed: 0_level_1'), ('Auckland', 'Unnamed: 1_level_1'), ('Bay of Plenty', 'Unnamed: 2_level_1'), ('Canterbury', 'Unnamed: 3_level_1'), ("Gisborne Hawke's Bay", 'Unnamed: 4_level_1'), ('Marlborough/NelsonTasman/West Coast', 'Unnamed: 5_level_1'), ('Manawatu/Wanganui-Taranaki', 'Unnamed: 6_level_1'), ('Northland', 'Unnamed: 7_level_1'), ('Otago Southland', 'Unnamed: 8_level_1'), ('Waikato', 'Unnamed: 9_level_1'), ('Wellington', 'Unnamed: 10_level_1'), ('Industry', 'Accounting'), ('Industry', 'Construction'), ('Industry', 'Education'), ('Industry', 'Health'), ('Industry', 'Hospitalty'), ('Industry', 'IT'), ('Industry', 'Manufacturing'), ('Industry', 'Primary'), ('Industry', 'Sales'), ('Industry', 'Other'), ('OCCUPATION', 'Managers'), ('OCCUPATION', 'Professionals'), ('OCCUPATION', 'Tech & Trades'), ('OCCUPATION', 'Community & Personal Services'), ('OCCUPATION', 'Clerical & Administration'), ('OCCUPATION', 'Sales'), ('OCCUPATION', 'Machinery Drivers'), ('OCCUPATION', 'Labourers'), ('OCCUPATION', 'highly skilled'), ('OCCUPATION', 'skilled'), ('OCCUPATION', 'semi-skilled'), ('OCCUPATION', 'low skilled'), ('OCCUPATION', 'unskilled'), ('OCCUPATION', 'Skilled'), ('OCCUPATION', 'Unskilled')]

# Processing column names
new_columns = []
for col in df_jobonline_all.columns:
    # Check and process region names
    if "Unnamed" in str(col[1]):
        new_columns.append(col[0])
    # Dealing with Industry-related columns
    elif col[0] == 'Industry':
        new_columns.append(f'ids_{col[1]}')
    # Dealing with Occupation-related columns
    elif col[0] == 'OCCUPATION':
        new_columns.append(f'ocp_{col[1]}')
    else:
        new_columns.append(col)

# update column names
df_jobonline_all.columns = new_columns

print("Updated columns:", df_jobonline_all.columns)

Updated columns: Index(['Date', 'Auckland', 'Bay of Plenty', 'Canterbury',
       'Gisborne Hawke's Bay', 'Marlborough/NelsonTasman/West Coast',
       'Manawatu/Wanganui-Taranaki', 'Northland', 'Otago Southland', 'Waikato',
       'Wellington', 'ids_Accounting', 'ids_Construction', 'ids_Education',
       'ids_Health', 'ids_Hospitalty', 'ids_IT', 'ids_Manufacturing',
       'ids_Primary', 'ids_Sales', 'ids_Other', 'ocp_Managers',
       'ocp_Professionals', 'ocp_Tech & Trades',
       'ocp_Community & Personal Services', 'ocp_Clerical & Administration',
       'ocp_Sales', 'ocp_Machinery Drivers', 'ocp_Labourers',
       'ocp_highly skilled', 'ocp_skilled', 'ocp_semi-skilled',
       'ocp_low skilled', 'ocp_unskilled', 'ocp_Skilled', 'ocp_Unskilled'],
      dtype='object')

from IPython.display import display, HTML

# Calculate the number of missing values for each row
missing_counts = df_jobonline_all.isna().sum(axis=1)

# Calculate the total number of columns in each row
total_columns = df_jobonline_all.shape[1]

# Calculate the percentage of missing values in each row
missing_percentage = (missing_counts / total_columns) * 100

# Create a new DataFrame showing the number and percentage of missing values in each row
missing_stats = pd.DataFrame({
    'Missing Values Count': missing_counts,
    'Missing Percentage': missing_percentage
})

# Setting up display configurations to avoid content being omitted
pd.set_option('display.max_rows', None)  
pd.set_option('display.max_columns', None) 
pd.set_option('display.width', None)  
pd.set_option('display.max_colwidth', None)  

# Use IPython's display function with HTML to create a scrolling viewframe to display the DataFrame.
display(HTML(missing_stats.to_html()))

# Delete lines 0 to 6
df_jobonline_all = df_jobonline_all.drop(index=range(7))  

df_jobonline_all.head()

import matplotlib.pyplot as plt

# Select columns starting with ‘ocp_’ to plot
ocp_columns = [col for col in df_jobonline_all.columns if col.startswith('ocp_')]
ocp_data = df_jobonline_all[ocp_columns]

plt.figure(figsize=(20, 6))

# plotting the 1st graph
# Set the diagram to the first position in a row of three columns
plt.subplot(1, 3, 1)  
for column in ocp_columns:
    plt.plot(df_jobonline_all['Date'], df_jobonline_all[column], marker=None, linestyle='-', label=column)

# Add legend and remove bottom frame
plt.legend(frameon=False)

# Select columns starting with ‘ids_’ to plot
ids_columns = [col for col in df_jobonline_all.columns if col.startswith('ids_')]
ids_data = df_jobonline_all[ids_columns]

# plotting the 2nd graph
plt.subplot(1, 3, 2)
for column in ids_columns:
    plt.plot(df_jobonline_all['Date'], df_jobonline_all[column], marker=None, linestyle='-', label=column)

plt.legend(frameon=False)

# Selecting variables to plot other than ‘Date’ and the above two groups of variables
other_columns = [col for col in df_jobonline_all.columns if col != 'Date' and col not in ocp_columns and col not in ids_columns]
other_data = df_jobonline_all[other_columns]

# plotting the 3rd graph
plt.subplot(1, 3, 3)
for column in other_columns:
    plt.plot(df_jobonline_all['Date'], df_jobonline_all[column], marker=None, linestyle='-', label=column)

plt.legend(frameon=False)

plt.tight_layout()

plt.show()

# import data
regionjob = pd.read_csv('../AAA/datasets/regionjob.csv')
regionjob.head()

regionjob.describe()

import pandas as pd
import matplotlib.pyplot as plt

# Selection of variables from columns 3 to 14
selected_columns = regionjob.iloc[:, 2:14]

# Setting the graphic size
plt.figure(figsize=(15, 10))

# Iterate through each column and plot a bar graph
for i, column in enumerate(selected_columns.columns):
    plt.subplot(3, 4, i + 1)
    plt.bar(regionjob.index, selected_columns[column], color='blue', edgecolor='none')
    plt.xlabel('Year')
    plt.ylabel(column)
    plt.title(column)

plt.tight_layout()
plt.show()

# Count the number and location of zeros for each variable
zero_counts = (regionjob == 0).sum()
zero_locations = {col: regionjob.index[regionjob[col] == 0].tolist() for col in regionjob.columns}


print("Number of zeros for each variable:")
print(zero_counts)

print("\nThe location of the zero value of each variable:")
for col, locations in zero_locations.items():
    print(f"{col}: {locations}")

Number of zeros for each variable:
Date                                       0
Type                                       0
Auckland                                   1
Waikato                                    1
Bay of Plenty                              1
Gisborne                                   1
Hawke's Bay                                1
Taranaki                                   1
Manawatu-Wanganui                          1
Wellington                                 1
Tasman, Nelson, Marlborough, West Coast    1
Canterbury                                 1
Otago                                      1
dtype: int64

The location of the zero value of each variable:
Date: []
Type: []
Auckland: [95]
Waikato: [95]
Bay of Plenty: [95]
Gisborne: [95]
Hawke's Bay: [95]
Taranaki: [95]
Manawatu-Wanganui: [95]
Wellington: [95]
Tasman, Nelson, Marlborough, West Coast: [95]
Canterbury: [95]
Otago: [95]

#View data at index [95]
print(regionjob.iloc[95])

Date                                                1999Q2
Type                                       Job Destruction
Auckland                                                 0
Waikato                                                  0
Bay of Plenty                                            0
Gisborne                                                 0
Hawke's Bay                                              0
Taranaki                                                 0
Manawatu-Wanganui                                        0
Wellington                                               0
Tasman, Nelson, Marlborough, West Coast                  0
Canterbury                                               0
Otago                                                    0
Name: 95, dtype: object

regionjob = regionjob[regionjob['Date'] != '1999Q2']
regionjob.head()

regionjob['Year'] = regionjob['Date'].str.extract(r'(\d{4})').astype(int)

# Aggregate data based on year and type and calculate the sum for each area
regionjob_yearly = regionjob.groupby(['Year', 'Type']).sum().reset_index()

regionjob_yearly.drop(columns='Date', inplace=True, errors='ignore') 


regionjob_yearly.head()

regionjob_pivot = regionjob_yearly.pivot_table(values=['Auckland', 'Waikato', 'Bay of Plenty', 'Gisborne', 
                              "Hawke's Bay", 'Taranaki', 'Manawatu-Wanganui', 'Wellington', 
                              'Tasman, Nelson, Marlborough, West Coast', 'Canterbury', 'Otago', 
                               ], index=['Type', 'Year'])
regionjob_pivot.head()

# Select data for ‘Job Creation’ and ‘Job Destruction’
job_creation = regionjob_pivot.loc['Job Creation']
job_destruction = regionjob_pivot.loc['Job Destruction']

# Plot the time series of ‘Job Creation’
plt.figure(figsize=(8, 3))
for column in job_creation.columns:
    plt.plot(job_creation.index, job_creation[column], label=column)
plt.title('Job Creation Over Years', fontsize=10)
plt.xticks(rotation=45,fontsize=9)  
plt.legend(loc='upper left', bbox_to_anchor=(1,1.03),fontsize=9) 

# Set the range of the x-axis to align with the minimum and maximum years of the data
plt.xlim(min(job_creation.index), max(job_creation.index))
plt.show()

# Plot time series of ‘Job Destruction’
plt.figure(figsize=(8, 3))
for column in job_destruction.columns:
    plt.plot(job_destruction.index, job_destruction[column], label=column)
plt.title('Job Destruction Over Years', fontsize=10)
plt.xticks(rotation=45,fontsize=9)  
plt.legend(loc='upper left', bbox_to_anchor=(1,1.03),fontsize=9) 

# Set the range of the x-axis to align with the minimum and maximum years of the data
plt.xlim(min(job_destruction.index), max(job_destruction.index))
plt.show()

# import data
file_path = "../AAA/datasets/Labour Force Status for people aged 15 to 64 years.csv"

labour_force_status = pd.read_csv(file_path) 

labour_force_status.head()

# Set graphic style to white background without grid
sns.set(style="white")

# Plot histogram using seaborn
bins = range(int(labour_force_status['Year'].min()), int(labour_force_status['Year'].max()) + 2)
plt.figure(figsize=(8, 4))
ax = sns.histplot(labour_force_status['Year'], bins=bins, kde=False, color='#34a4eb', edgecolor=None)

# Set up graph titles and axis labels
plt.title('Histogram of Year')
ax.set_xlabel('')  
plt.ylabel('Frequency',fontsize=9)

# Set up labels to be displayed every 5 years
tick_labels = range(int(labour_force_status['Year'].min()), int(labour_force_status['Year'].max()) + 1, 5)
plt.xticks(tick_labels,fontsize=9)  

# Reduce the thickness of the frame lines
for spine in ax.spines.values():
    spine.set_linewidth(0.5)

plt.show()

labour_force_status.describe()

labour_force_status = labour_force_status.iloc[1:]
labour_force_status.head()

# Convert all columns except ‘Year’ to numeric values
for col in labour_force_status.columns[1:]:  
    labour_force_status[col] = pd.to_numeric(labour_force_status[col], errors='coerce')

# Set canvas size and subgraph layout
fig, axes = plt.subplots(nrows=2, ncols=4, figsize=(20, 9))
axes = axes.flatten()  

# Plot the KDEs for each variable
for i, column in enumerate(labour_force_status.columns):
    sns.kdeplot(data=labour_force_status, x=column, ax=axes[i], fill=True)
    axes[i].set_title(column)
    axes[i].set_xlabel('')  
    axes[i].set_ylabel('Density')  

plt.tight_layout()
plt.show()

# import data
file_path = "../AAA/datasets/age median wage.csv"

age_median_wage = pd.read_csv(file_path) 

age_median_wage.head()

missing_values_count = age_median_wage.isna().sum()
print(missing_values_count)

Date              0
15-19             0
20-24             0
25-29             0
30-34             0
35-39             0
40-44             0
45-49             0
50-54             0
55-59             0
60-64             0
65                0
Total All Ages    0
dtype: int64

sns.set(style="whitegrid")
age_median_wage_long = pd.melt(age_median_wage, id_vars=['Date'], var_name='Age Group', value_name='Median Wage')

# Plot box plots, including wage data for all age groups
plt.figure(figsize=(10, 5))
ax = sns.boxplot(x='Age Group', y='Median Wage', data=age_median_wage_long)

plt.xticks(rotation=45)
plt.title('Median Wage Distribution by Age Group')
plt.xlabel('')
plt.ylabel('')
plt.show()

# Extraction year
age_median_wage['Year'] = age_median_wage['Date'].str[:4].astype(int)

# Ensure that all non-date columns are of numeric type
numeric_cols = age_median_wage.select_dtypes(include=[np.number]).columns.tolist()

if 'Year' in numeric_cols:
    numeric_cols.remove('Year')
    
# Group by year and calculate the average of the numerical columns
age_median_wage_year = age_median_wage.groupby('Year',as_index=True)[numeric_cols].mean()

age_median_wage_year = age_median_wage_year.reset_index()
age_median_wage_year.iloc[:, 1:] = age_median_wage_year.iloc[:, 1:].round(1)
age_median_wage_year.head()

# import data
file_path = "../AAA/datasets/GDP_region.csv"
GDP_region = pd.read_csv(file_path) 

GDP_region

GDP_region.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 24 entries, 0 to 23
Data columns (total 19 columns):
 #   Column              Non-Null Count  Dtype 
---  ------              --------------  ----- 
 0   Year                24 non-null     int64 
 1   Northland           24 non-null     object
 2   Auckland            24 non-null     object
 3   Waikato             24 non-null     object
 4   Bay of Plenty       24 non-null     object
 5   Gisborne            24 non-null     object
 6   Hawke's Bay         24 non-null     object
 7   Taranaki            24 non-null     object
 8   Manawatu-Whanganui  24 non-null     object
 9   Wellington          24 non-null     object
 10  West Coast          24 non-null     object
 11  Canterbury          24 non-null     object
 12  Otago               24 non-null     object
 13  Southland           24 non-null     object
 14  Marlborough         24 non-null     object
 15  Tasman/Nelson       24 non-null     object
 16  Total North Island  24 non-null     object
 17  Total South Island  24 non-null     object
 18  New Zealand         24 non-null     object
dtypes: int64(1), object(18)
memory usage: 3.7+ KB

# Replace ‘...’ for NaN
GDP_region.replace('..', pd.NA, inplace=True)

GDP_region = GDP_region.apply(pd.to_numeric, errors='coerce')
print(GDP_region.info())

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 24 entries, 0 to 23
Data columns (total 19 columns):
 #   Column              Non-Null Count  Dtype  
---  ------              --------------  -----  
 0   Year                24 non-null     int64  
 1   Northland           23 non-null     float64
 2   Auckland            23 non-null     float64
 3   Waikato             23 non-null     float64
 4   Bay of Plenty       23 non-null     float64
 5   Gisborne            23 non-null     float64
 6   Hawke's Bay         23 non-null     float64
 7   Taranaki            23 non-null     float64
 8   Manawatu-Whanganui  23 non-null     float64
 9   Wellington          23 non-null     float64
 10  West Coast          23 non-null     float64
 11  Canterbury          23 non-null     float64
 12  Otago               23 non-null     float64
 13  Southland           23 non-null     float64
 14  Marlborough         23 non-null     float64
 15  Tasman/Nelson       23 non-null     float64
 16  Total North Island  23 non-null     float64
 17  Total South Island  23 non-null     float64
 18  New Zealand         23 non-null     float64
dtypes: float64(18), int64(1)
memory usage: 3.7 KB
None

GDP_region.set_index('Year', inplace=True)

plt.figure(figsize=(8, 4))
for column in GDP_region.columns:
    plt.plot(GDP_region.index, GDP_region[column], marker='o', label=column)

plt.title('GDP Trends by Region')
plt.grid(False)
plt.show()

# Calculate the growth rate for each region from 2021 to 2022
growth_rates = (GDP_region.loc[2022] - GDP_region.loc[2021]) / GDP_region.loc[2021]

# Projected data for 2023 based on data for 2022 and calculated growth rates
GDP_region.loc[2023] = GDP_region.loc[2022] * (1 + growth_rates)

print(GDP_region.loc[2023])

Northland               9663.231164
Auckland              136314.175126
Waikato                32019.992728
Bay of Plenty          21169.427548
Gisborne                2381.703901
Hawke's Bay            10758.225839
Taranaki                9831.115637
Manawatu-Whanganui     14186.718943
Wellington             44215.383955
West Coast              1812.109865
Canterbury             44055.669936
Otago                  15275.914152
Southland               8258.371521
Marlborough             3371.313419
Tasman/Nelson           6531.251164
Total North Island    280519.405016
Total South Island     79253.753487
New Zealand           359772.985932
Name: 2023, dtype: float64

GDP_region.reset_index(inplace=True)

# Data formatting adjustments
GDP_region.iloc[:, 1:] = GDP_region.iloc[:, 1:].round(1)

GDP_region

# import data
file_path = "../AAA/datasets/GDP_industry.csv"
GDP_industry = pd.read_csv(file_path) 

GDP_industry.head()

GDP_industry.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 23 entries, 0 to 22
Data columns (total 25 columns):
 #   Column                                                                 Non-Null Count  Dtype  
---  ------                                                                 --------------  -----  
 0   Year                                                                   23 non-null     int64  
 1   Agriculture                                                            23 non-null     int64  
 2   Forestry, Fishing, and Mining                                          23 non-null     int64  
 3   Forestry, Fishing, Mining, Electricity, Gas, Water and Waste Services  23 non-null     int64  
 4   Primary Manufacturing                                                  23 non-null     int64  
 5   Other Manufacturing                                                    23 non-null     int64  
 6   Manufacturing                                                          23 non-null     int64  
 7   Electricity, Gas, Water, and Waste services                            23 non-null     int64  
 8   Construction                                                           23 non-null     int64  
 9   Wholesale Trade                                                        23 non-null     int64  
 10  Retail Trade                                                           23 non-null     int64  
 11  Accommodation and Food Services                                        16 non-null     float64
 12  Accommodation                                                          23 non-null     int64  
 13  Food and beverage services                                             23 non-null     int64  
 14  Transport, Postal and Warehousing                                      23 non-null     int64  
 15  Information Media, Telecommunications and Other Services               23 non-null     int64  
 16  Financial and Insurance Services                                       23 non-null     int64  
 17  Rental, Hiring and Real Estate Services                                23 non-null     int64  
 18  Owner-Occupied Property Operation                                      23 non-null     int64  
 19  Professional, Scientific, and Technical Services                       23 non-null     int64  
 20  Administrative and Support Services                                    23 non-null     int64  
 21  Public Administration and Safety                                       23 non-null     int64  
 22  Education and Training                                                 23 non-null     int64  
 23  Health Care and Social Assistance                                      23 non-null     int64  
 24  Total All Industries                                                   23 non-null     int64  
dtypes: float64(1), int64(24)
memory usage: 4.6 KB

print(GDP_industry['Accommodation and Food Services'])

0     2086.0
1     2317.0
2     2521.0
3     2477.0
4     2832.0
5     3148.0
6     3216.0
7     3365.0
8     3649.0
9     3505.0
10    3789.0
11    3857.0
12    3940.0
13    4124.0
14    4368.0
15    4763.0
16       NaN
17       NaN
18       NaN
19       NaN
20       NaN
21       NaN
22       NaN
Name: Accommodation and Food Services, dtype: float64

# Calculate the correlation coefficient matrix
corr_matrix = GDP_industry.drop('Year', axis=1).corr()

# Plot heat map
plt.figure(figsize=(8, 6))  
sns.heatmap(corr_matrix, annot=False, cmap='coolwarm', cbar=True)
plt.show()

from sklearn.linear_model import LinearRegression

# Split data into parts with and without missing values
train_data = GDP_industry.dropna(subset=['Accommodation and Food Services'])
test_data = GDP_industry[GDP_industry['Accommodation and Food Services'].isna()]

# Define the independent and dependent variables
X_train = train_data[['Food and beverage services']]
y_train = train_data['Accommodation and Food Services']
X_test = test_data[['Food and beverage services']]

# Build a linear regression model
model = LinearRegression()
model.fit(X_train, y_train)

# Predicted missing values
predicted_values = model.predict(X_test)

# Impute missing value
GDP_industry.loc[GDP_industry['Accommodation and Food Services'].isna(), 'Accommodation and Food Services'] = predicted_values

# Display of final data
GDP_industry['Accommodation and Food Services'] = GDP_industry['Accommodation and Food Services'].astype('int64')
GDP_industry['Accommodation and Food Services']

0     2086
1     2317
2     2521
3     2477
4     2832
5     3148
6     3216
7     3365
8     3649
9     3505
10    3789
11    3857
12    3940
13    4124
14    4368
15    4763
16    5327
17    5947
18    6247
19    6471
20    6823
21    6002
22    6851
Name: Accommodation and Food Services, dtype: int64

# Convert a date string to a date object
df_jobonline_all['Date'] = pd.to_datetime(df_jobonline_all['Date'])

# Calculate quarters and format dates
df_jobonline_all['Date'] = df_jobonline_all['Date'].dt.year.astype(str) + 'Q' + ((df_jobonline_all['Date'].dt.month - 1) // 3 + 1).astype(str)

df_jobonline_all['Year'] = df_jobonline_all['Date'].str[:4].astype(int)
numeric_cols = df_jobonline_all.select_dtypes(include=[np.number]).columns.tolist()

if 'Year' in numeric_cols:
    numeric_cols.remove('Year')
    
# Grouping by year and averaging the numerical columns
job_online = df_jobonline_all.groupby('Year',as_index=True)[numeric_cols].mean()

job_online.reset_index(drop=False, inplace=True)
job_online.head()

# Get all the columns except ‘Year’
columns_to_rename = [col for col in job_online.columns if col != 'Year']

# Construct a dictionary that maps old column names to new column names
rename_dict = {col: 'AVI_' + col for col in columns_to_rename}

# Use the rename() method to rename a column
job_online =job_online.rename(columns=rename_dict)

job_online.head()

# Add prefixes and rename variables

job_creation.reset_index(drop=False, inplace=True)
# Get all the columns except ‘Year’
columns_to_rename = [col for col in job_creation.columns if col != 'Year']

# Construct a dictionary that maps old column names to new column names
rename_dict = {col: 'job_creation_' + col for col in columns_to_rename}

job_creation = job_creation.rename(columns=rename_dict)

job_creation.head()

# Add prefixes and rename variables

job_destruction.reset_index(drop=False, inplace=True)
columns_to_rename = [col for col in job_destruction.columns if col != 'Year']

rename_dict = {col: 'job_destruction_' + col for col in columns_to_rename}

job_destruction = job_destruction.rename(columns=rename_dict)

job_destruction.head()

job_creation['Year'] = job_creation['Year'].astype(int)
job_destruction['Year'] = job_destruction['Year'].astype(int)

# Add prefixes and rename variables
columns_to_rename = [col for col in age_median_wage_year.columns if col != 'Year']

rename_dict = {col: 'median_wage_' + col for col in columns_to_rename}
age_median_wage_year = age_median_wage_year.rename(columns=rename_dict)

age_median_wage_year.head()

# Add prefixes and rename variables
columns_to_rename = [col for col in GDP_region.columns if col != 'Year']

rename_dict = {col: 'GDP_' + col for col in columns_to_rename}
GDP_region = GDP_region.rename(columns=rename_dict)

GDP_region.head()

# Add prefixes and rename variables
columns_to_rename = [col for col in GDP_industry.columns if col != 'Year']

rename_dict = {col: 'GDP_' + col for col in columns_to_rename}

GDP_industry = GDP_industry.rename(columns=rename_dict)

GDP_industry.head()

def merge_datasets(*datasets):

    merged_dataset = datasets[0]  # Initialize with the first dataset
    
    # Iterate over the remaining datasets and merge them one by one
    for dataset in datasets[1:]:
        merged_dataset = pd.merge(merged_dataset, dataset, on='Year', how='inner')
    
    return merged_dataset

merged_data = merge_datasets(job_creation, job_destruction, labour_force_status, job_online,age_median_wage_year,GDP_region, GDP_industry)
merged_data

import dask.dataframe as dd

# Convert to Dask DataFrame
ddf = dd.from_pandas(merged_data, npartitions=10)

# Change float64 to float32. Also change int64 to int32.
for column in merged_data.columns:
    if merged_data[column].dtype == 'float64':
        merged_data[column] = merged_data[column].astype('float32')
    if merged_data[column].dtype == 'int64':
        merged_data[column] = merged_data[column].astype('int32')

# Define a function to replace special characters in column names
def clean_column_names(column_name):
    return column_name.replace(' ', '_').replace('/', '_').replace("'", "").replace('&', 'and').replace(',', '_').replace('-', '_')

# Apply this function to all columns
merged_data.columns = [clean_column_names(col) for col in merged_data.columns]

# Save dataset to HDF5 file
merged_data.to_hdf('merged_data.h5', key='data', mode='w', format='table', data_columns=True)

sns.set_theme(style="whitegrid")

plot_data = pd.melt(merged_data, id_vars=['Year'], value_vars=['GDP_Total_North_Island', 'GDP_Total_South_Island', 'GDP_New_Zealand'], var_name='Region', value_name='GDP')
plt.figure(figsize=(14, 7))
sns.lineplot(data=plot_data, x='Year', y='GDP', hue='Region', linewidth=2.5)

plt.xlabel('Year')
plt.ylabel('GDP')
plt.title('GDP Distribution in North Island, South Island and New Zealand from 2010 to 2022')
plt.figtext(0.95, 0.02, 'Source: GDP_region.csv', horizontalalignment='right', verticalalignment='bottom')

Text(0.95, 0.02, 'Source: GDP_region.csv')

columns_choose2 = [
    'GDP_Agriculture',
    'GDP_Forestry__Fishing__and_Mining',
    'GDP_Forestry__Fishing__Mining__Electricity__Gas__Water_and_Waste_Services',
    'GDP_Manufacturing',
    'GDP_Electricity__Gas__Water__and_Waste_services',
    'GDP_Construction',
    'GDP_Wholesale_Trade',
    'GDP_Retail_Trade',
    'GDP_Accommodation_and_Food_Services',
    'GDP_Accommodation',
    'GDP_Food_and_beverage_services',
    'GDP_Transport__Postal_and_Warehousing',
    'GDP_Information_Media__Telecommunications_and_Other_Services',
    'GDP_Financial_and_Insurance_Services',
    'GDP_Rental__Hiring_and_Real_Estate_Services',
    'GDP_Owner_Occupied_Property_Operation',
    'GDP_Professional__Scientific__and_Technical_Services',
    'GDP_Administrative_and_Support_Services',
    'GDP_Public_Administration_and_Safety',
    'GDP_Education_and_Training',
    'GDP_Health_Care_and_Social_Assistance']

years = merged_data['Year']
vals = [merged_data[col].values for col in columns_choose2]

plt.figure(figsize=(16, 9), dpi=80)
colors = [plt.cm.Spectral(i / float(len(columns_choose2) - 1)) for i in range(len(columns_choose2))]

plt.stackplot(years, vals, labels=columns_choose2, colors=colors)
plt.legend(loc='center left', bbox_to_anchor=(1, 0.5), frameon=True)
plt.title('GDP Distribution by Industry in New Zealand from 2010 to 2022', fontsize=22)
plt.xlabel('Year')
plt.ylabel('GDP')
plt.xticks(rotation=45)
plt.figtext(0.95, 0.02, 'Source: industryGDP.csv', horizontalalignment='right', verticalalignment='bottom')

Text(0.95, 0.02, 'Source: industryGDP.csv')

plt.figure(figsize=(14, 5))

plt.plot(merged_industrycontribution['Industry'], merged_industrycontribution['GDP_2022(M)'], label='Contribution of GDP 2022')
plt.plot(merged_industrycontribution['Industry'], merged_industrycontribution['GDP_2023(M)'], label='Contribution of GDP 2023')
average_gdp_2022 = merged_industrycontribution['GDP_2022(M)'].mean()
average_gdp_2023 = merged_industrycontribution['GDP_2023(M)'].mean()

plt.axhline(y=average_gdp_2022, color='skyblue', linestyle='--', label='Average GDP 2022')
plt.axhline(y=average_gdp_2023, color='orange', linestyle='--', label='Average GDP 2023')

plt.ylabel('GDP')
plt.title("Contribution of Each Industry to New Zealand GDP in 2022-2023")
plt.xticks(rotation=45,fontsize=9)
plt.legend()
plt.subplots_adjust(bottom=0.30, right=0.85)
plt.figtext(0.95, 0.02, 'Source: API https://rep.infometrics.co.nz ', horizontalalignment='right', verticalalignment='bottom')

Text(0.95, 0.02, 'Source: API https://rep.infometrics.co.nz ')

plt.figure(figsize=(14, 5))

plt.plot(merged_industrycontribution['Industry'], merged_industrycontribution['GDP_2022(M)'], label='Contribution of GDP 2022')
plt.plot(merged_industrycontribution['Industry'], merged_industrycontribution['GDP_2023(M)'], label='Contribution of GDP 2023')
plt.plot(merged_industrycontribution['Industry'], merged_industrycontribution['Employment_2022'],color='Green', linestyle='--', label='Jobs Numbers 2022')
plt.plot(merged_industrycontribution['Industry'], merged_industrycontribution['Employment_2023'], color='Green',label='Jobs Numbers 2023')

plt.title("Contribution of Each Industry to New Zealand GDP and Job Numbers in 2022-2023")
plt.xticks(rotation=45,fontsize=9)
plt.legend(fontsize=10, loc='best', bbox_to_anchor=(1, 1))
plt.subplots_adjust(bottom=0.30, right=0.85)
plt.figtext(0.95, 0.02, 'Source: API https://rep.infometrics.co.nz ', horizontalalignment='right', verticalalignment='bottom')

Text(0.95, 0.02, 'Source: API https://rep.infometrics.co.nz ')

summary_table

plt.figure(figsize=(14, 7))

width = 0.3
x = np.arange(len(summary_table.index))

plt.bar(x - width, summary_table['Good'], width=width, label='Good',color='tan')
plt.bar(x, summary_table['Average'], width=width, label='Average',color='peru')
plt.bar(x + width, summary_table['Poor'], width=width, label='Poor',color='maroon')

plt.xlabel('Vocations')
plt.ylabel('Classified Numbers')
plt.title(' Job Opportunities by 6 Main Industries in New Zealand')
plt.xticks(x, summary_table.index, rotation=45, ha='right', fontsize=12)
plt.legend(title='Job Opportunities')

plt.subplots_adjust(bottom=0.30, right=0.85)
plt.figtext(0.95, 0.02, 'Source: Web Scraping https://www.careers.govt.nz', horizontalalignment='right', verticalalignment='bottom')

Text(0.95, 0.02, 'Source: Web Scraping https://www.careers.govt.nz')

plt.figure(figsize=(14, 7))

colors = sns.color_palette(['tan', 'peru', 'maroon'])

p1 = plt.bar(summary_table.index, summary_table['Good'], color=colors[0], label='Good')
p2 = plt.bar(summary_table.index, summary_table['Average'], bottom=summary_table['Good'], color=colors[1], label='Average')
p3 = plt.bar(summary_table.index, summary_table['Poor'], bottom=summary_table['Good'] + summary_table['Average'], color=colors[2], label='Poor')

plt.xlabel('Vocations')
plt.ylabel('Classified Numbers')
plt.title('Job Opportunities by 6 Main Industries in New Zealand- Accumulated')
plt.xticks(rotation=45, ha='right', fontsize=12)
plt.legend(title='Job Opportunities')
plt.subplots_adjust(bottom=0.30, right=0.85)
plt.figtext(0.95, 0.02, 'Source: Web Scraping https://www.careers.govt.nz', horizontalalignment='right', verticalalignment='bottom')

Text(0.95, 0.02, 'Source: Web Scraping https://www.careers.govt.nz')

job_online

_ = job_online.hist(bins=int(np.sqrt(len(job_online))),facecolor='grey', figsize=(18, 18), xlabelsize=8)

avi_columns = ['AVI_Auckland', 'AVI_Bay_of_Plenty', 'AVI_Canterbury', 'AVI_Gisborne_Hawkes_Bay',
    'AVI_Marlborough_NelsonTasman_West_Coast', 'AVI_Manawatu_Wanganui_Taranaki',
    'AVI_Northland', 'AVI_Otago_Southland', 'AVI_Waikato', 'AVI_Wellington']

plot_data = merged_data.melt(id_vars=['Year'], value_vars=avi_columns, var_name='Variable', value_name='Value')

g = sns.relplot(x='Year', y='Value', hue='Variable', size='Value', sizes=(40, 400), alpha=.5, palette="bright", height=6, data=plot_data, aspect=2)
g.set_axis_labels("Year", "AVI")
g.fig.suptitle("All Vacancy Indices (AVIs) by Region from 2010-2022", fontsize=16)

C:\Users\Alene\anaconda3\Lib\site-packages\seaborn\axisgrid.py:118: UserWarning: The figure layout has changed to tight
  self._figure.tight_layout(*args, **kwargs)

Text(0.5, 0.98, 'All Vacancy Indices (AVIs) by Region from 2010-2022')

columns_with_index = {i: col for i, col in enumerate(merged_data.columns)}
for index, column in columns_with_index.items():
    print(f"Column {index}: {column}")

Column 0: Year
Column 1: job_creation_Auckland
Column 2: job_creation_Bay_of_Plenty
Column 3: job_creation_Canterbury
Column 4: job_creation_Gisborne
Column 5: job_creation_Hawkes_Bay
Column 6: job_creation_Manawatu_Wanganui
Column 7: job_creation_Otago
Column 8: job_creation_Taranaki
Column 9: job_creation_Tasman__Nelson__Marlborough__West_Coast
Column 10: job_creation_Waikato
Column 11: job_creation_Wellington
Column 12: job_destruction_Auckland
Column 13: job_destruction_Bay_of_Plenty
Column 14: job_destruction_Canterbury
Column 15: job_destruction_Gisborne
Column 16: job_destruction_Hawkes_Bay
Column 17: job_destruction_Manawatu_Wanganui
Column 18: job_destruction_Otago
Column 19: job_destruction_Taranaki
Column 20: job_destruction_Tasman__Nelson__Marlborough__West_Coast
Column 21: job_destruction_Waikato
Column 22: job_destruction_Wellington
Column 23: Not_in_Labour_Force
Column 24: Working_Age_Population
Column 25: Labour_Force_Participation_Rate
Column 26: Unemployment_Rate
Column 27: Employment_Rate
Column 28: Total_Labour_Force
Column 29: AVI_Auckland
Column 30: AVI_Bay_of_Plenty
Column 31: AVI_Canterbury
Column 32: AVI_Gisborne_Hawkes_Bay
Column 33: AVI_Marlborough_NelsonTasman_West_Coast
Column 34: AVI_Manawatu_Wanganui_Taranaki
Column 35: AVI_Northland
Column 36: AVI_Otago_Southland
Column 37: AVI_Waikato
Column 38: AVI_Wellington
Column 39: AVI_ids_Accounting
Column 40: AVI_ids_Construction
Column 41: AVI_ids_Education
Column 42: AVI_ids_Health
Column 43: AVI_ids_Hospitalty
Column 44: AVI_ids_IT
Column 45: AVI_ids_Manufacturing
Column 46: AVI_ids_Primary
Column 47: AVI_ids_Sales
Column 48: AVI_ids_Other
Column 49: AVI_ocp_Managers
Column 50: AVI_ocp_Professionals
Column 51: AVI_ocp_Tech_and_Trades
Column 52: AVI_ocp_Community_and_Personal_Services
Column 53: AVI_ocp_Clerical_and_Administration
Column 54: AVI_ocp_Sales
Column 55: AVI_ocp_Machinery_Drivers
Column 56: AVI_ocp_Labourers
Column 57: AVI_ocp_highly_skilled
Column 58: AVI_ocp_skilled
Column 59: AVI_ocp_semi_skilled
Column 60: AVI_ocp_low_skilled
Column 61: AVI_ocp_unskilled
Column 62: AVI_ocp_Skilled
Column 63: AVI_ocp_Unskilled
Column 64: median_wage_15_19
Column 65: median_wage_20_24
Column 66: median_wage_25_29
Column 67: median_wage_30_34
Column 68: median_wage_35_39
Column 69: median_wage_40_44
Column 70: median_wage_45_49
Column 71: median_wage_50_54
Column 72: median_wage_55_59
Column 73: median_wage_60_64
Column 74: median_wage_65
Column 75: median_wage_Total_All_Ages
Column 76: GDP_Northland
Column 77: GDP_Auckland
Column 78: GDP_Waikato
Column 79: GDP_Bay_of_Plenty
Column 80: GDP_Gisborne
Column 81: GDP_Hawkes_Bay
Column 82: GDP_Taranaki
Column 83: GDP_Manawatu_Whanganui
Column 84: GDP_Wellington
Column 85: GDP_West_Coast
Column 86: GDP_Canterbury
Column 87: GDP_Otago
Column 88: GDP_Southland
Column 89: GDP_Marlborough
Column 90: GDP_Tasman_Nelson
Column 91: GDP_Total_North_Island
Column 92: GDP_Total_South_Island
Column 93: GDP_New_Zealand
Column 94: GDP_Agriculture
Column 95: GDP_Forestry__Fishing__and_Mining
Column 96: GDP_Forestry__Fishing__Mining__Electricity__Gas__Water_and_Waste_Services
Column 97: GDP_Primary_Manufacturing
Column 98: GDP_Other_Manufacturing
Column 99: GDP_Manufacturing
Column 100: GDP_Electricity__Gas__Water__and_Waste_services
Column 101: GDP_Construction
Column 102: GDP_Wholesale_Trade
Column 103: GDP_Retail_Trade
Column 104: GDP_Accommodation_and_Food_Services
Column 105: GDP_Accommodation
Column 106: GDP_Food_and_beverage_services
Column 107: GDP_Transport__Postal_and_Warehousing
Column 108: GDP_Information_Media__Telecommunications_and_Other_Services
Column 109: GDP_Financial_and_Insurance_Services
Column 110: GDP_Rental__Hiring_and_Real_Estate_Services
Column 111: GDP_Owner_Occupied_Property_Operation
Column 112: GDP_Professional__Scientific__and_Technical_Services
Column 113: GDP_Administrative_and_Support_Services
Column 114: GDP_Public_Administration_and_Safety
Column 115: GDP_Education_and_Training
Column 116: GDP_Health_Care_and_Social_Assistance
Column 117: GDP_Total_All_Industries

columns_choose = [77, 76, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90]

years = merged_data['Year']
vals = [merged_data.iloc[:, col].values for col in columns_choose]
labels = [merged_data.columns[col] for col in columns_choose]

plt.figure(figsize=(16, 9), dpi=80)
colors = [plt.cm.Spectral(i / float(len(columns_choose) - 1)) for i in range(len(columns_choose))]

plt.stackplot(years, vals, labels=labels, colors=colors)
plt.legend(loc='center left', bbox_to_anchor=(1, 0.5), frameon=True)
plt.title('GDP Contribution by Region from 2010 to 2022', fontsize=22)
plt.xlabel('Year')
plt.ylabel('GDP')
plt.xticks(rotation=45)

(array([2008., 2010., 2012., 2014., 2016., 2018., 2020., 2022., 2024.]),
 [Text(2008.0, 0, '2008'),
  Text(2010.0, 0, '2010'),
  Text(2012.0, 0, '2012'),
  Text(2014.0, 0, '2014'),
  Text(2016.0, 0, '2016'),
  Text(2018.0, 0, '2018'),
  Text(2020.0, 0, '2020'),
  Text(2022.0, 0, '2022'),
  Text(2024.0, 0, '2024')])

UnemploymentRate_median = merged_data['Unemployment_Rate'].median()
UnemploymentRate_median

5.599999904632568

AVI_Auckland_median = merged_data['AVI_Auckland'].median()
AVI_Auckland_median

146.18475341796875

unemployment_rate_label = np.where(merged_data['Unemployment_Rate'] > 5.6, 'High', 'Low')
avi_auckland_label = np.where(merged_data['AVI_Auckland'] > 146.18475, 'High', 'Low')
merged_data1 = merged_data.copy()
merged_data1

unemployment_rate_label = np.where(merged_data['Unemployment_Rate'] > 5.6, 'High', 'Low')
avi_auckland_label = np.where(merged_data['AVI_Auckland'] > 146.18475, 'High', 'Low')

new_columns = pd.DataFrame({'Unemployment Rate Classified': unemployment_rate_label,'AVI Auckland Classified': avi_auckland_label})
merged_data = pd.concat([merged_data, new_columns], axis=1)
merged_data1 = merged_data.copy()

merged_data1

labels = ['E', 'D', 'C', 'B', 'A']

bins = [merged_data1['GDP_Auckland'].min(), 70000, 85000, 95000, 110000, merged_data1['GDP_Auckland'].max()]

merged_data1['GDP_Auckland_Grade'] = pd.cut(merged_data1['GDP_Auckland'], bins=bins, labels=labels, include_lowest=True)

merged_data1[['GDP_Auckland', 'GDP_Auckland_Grade']]

merged_data1

merged_data1.pivot_table(values='AVI_Auckland',index=['GDP_Auckland_Grade', 'AVI Auckland Classified'], aggfunc='mean' )

merged_data1.pivot_table(values=['AVI_Auckland'], index=['Unemployment Rate Classified','GDP_Auckland_Grade'], columns='AVI Auckland Classified')

merged_data1.pivot_table(values='AVI_Auckland', index=['Unemployment Rate Classified','GDP_Auckland_Grade'], columns='AVI Auckland Classified', aggfunc=len, margins=True)

crosstab_AVI_Auckland = pd.crosstab(index=[merged_data1['Unemployment Rate Classified'], merged_data1['GDP_Auckland_Grade']],
    columns=merged_data1['AVI Auckland Classified'],
    values=merged_data1['AVI_Auckland'],
    aggfunc='count',
    margins=True)
crosstab_AVI_Auckland

Unemployment_AVIAuckland = merged_data1.groupby('Unemployment Rate Classified')['GDP_Auckland'].sum()

Unemployment_AVIAuckland.plot(kind='bar', figsize=(10, 6), color='Orange', edgecolor='black')
plt.title('Unemployment Rate in New Zealand Relates to GDP Auckland')
plt.xlabel('Unemployment Rate Classified')
plt.ylabel('GDP Auckland')

Text(0, 0.5, 'GDP Auckland')

Unemployment_AVIAuckland = merged_data1.groupby('Unemployment Rate Classified')['AVI_Auckland'].sum()

Unemployment_AVIAuckland.plot(kind='bar', figsize=(10, 6), color='blue', edgecolor='black')
plt.title('Unemployment Rate in New Zealand Relates to AVI Auckland')
plt.xlabel('Unemployment Rate Classified')
plt.ylabel('AVI Auckland')

Text(0, 0.5, 'AVI Auckland')

regionjob

grouped_auckland = regionjob.groupby(['Auckland','Type'])
grouped_auckland.groups

{(2000, 'Job Destruction'): [97], (2220, 'Job Destruction'): [109], (2250, 'Job Destruction'): [105], (2390, 'Job Destruction'): [117], (2440, 'Job Destruction'): [121], (2510, 'Job Destruction'): [96], (2580, 'Job Destruction'): [120], (2600, 'Job Destruction'): [100], (2610, 'Job Creation'): [15], (2620, 'Job Destruction'): [124], (2630, 'Job Destruction'): [153], (2660, 'Job Destruction'): [104], (2680, 'Job Destruction'): [99], (2700, 'Job Destruction'): [116], (2710, 'Job Creation'): [1], (2720, 'Job Destruction'): [112, 145], (2770, 'Job Destruction'): [107, 141], (2820, 'Job Destruction'): [161], (2860, 'Job Destruction'): [101], (2870, 'Job Creation'): [18], (2880, 'Job Destruction'): [148], (2950, 'Job Destruction'): [129], (2960, 'Job Destruction'): [113], (3010, 'Job Creation'): [19], (3040, 'Job Creation'): [2], (3060, 'Job Creation'): [6, 10, 42], (3060, 'Job Destruction'): [184], (3080, 'Job Destruction'): [108], (3090, 'Job Creation'): [53], (3130, 'Job Creation'): [12], (3130, 'Job Destruction'): [114], (3140, 'Job Destruction'): [152], (3150, 'Job Creation'): [41], (3180, 'Job Destruction'): [149, 165], (3250, 'Job Destruction'): [143], (3260, 'Job Creation'): [37], (3260, 'Job Destruction'): [156], (3280, 'Job Creation'): [9], (3290, 'Job Creation'): [21], (3290, 'Job Destruction'): [111, 169], (3300, 'Job Destruction'): [125], (3330, 'Job Creation'): [50], (3330, 'Job Destruction'): [118, 157], (3340, 'Job Creation'): [3, 5], (3340, 'Job Destruction'): [110, 185], (3360, 'Job Creation'): [38, 39], (3360, 'Job Destruction'): [140], (3370, 'Job Creation'): [22], (3420, 'Job Creation'): [30], (3440, 'Job Destruction'): [128], (3450, 'Job Creation'): [46], (3470, 'Job Destruction'): [115, 181], (3490, 'Job Creation'): [14], (3490, 'Job Destruction'): [127], (3510, 'Job Destruction'): [132, 155], (3520, 'Job Creation'): [85], (3520, 'Job Destruction'): [164], (3570, 'Job Destruction'): [131], (3580, 'Job Destruction'): [173], (3590, 'Job Creation'): [49], (3600, 'Job Destruction'): [133, 137], (3680, 'Job Creation'): [13], (3680, 'Job Destruction'): [103], (3700, 'Job Creation'): [4, 23, 31], (3740, 'Job Destruction'): [119], (3780, 'Job Destruction'): [151], (3790, 'Job Destruction'): [150], (3810, 'Job Creation'): [26], (3820, 'Job Creation'): [40], (3820, 'Job Destruction'): [102], (3840, 'Job Destruction'): [136], (3850, 'Job Destruction'): [160], (3860, 'Job Creation'): [58], (3880, 'Job Creation'): [25], (3890, 'Job Creation'): [35], (3920, 'Job Creation'): [17, 27], (3920, 'Job Destruction'): [147], (3930, 'Job Destruction'): [166, 168], (3950, 'Job Destruction'): [186], (3970, 'Job Creation'): [57], (3980, 'Job Creation'): [33], (4000, 'Job Creation'): [8], (4020, 'Job Creation'): [59], (4030, 'Job Creation'): [29], (4040, 'Job Creation'): [61], (4060, 'Job Destruction'): [122], (4080, 'Job Creation'): [86], (4090, 'Job Destruction'): [163], (4100, 'Job Destruction'): [167, 189], (4130, 'Job Destruction'): [144, 162], (4150, 'Job Destruction'): [130], (4160, 'Job Creation'): [87], (4190, 'Job Creation'): [69], (4190, 'Job Destruction'): [180], (4200, 'Job Creation'): [24, 77], (4220, 'Job Creation'): [81], (4240, 'Job Destruction'): [126], (4250, 'Job Creation'): [55, 66], (4290, 'Job Destruction'): [138], (4350, 'Job Creation'): [82], ...}

grouped_auckland.groups[3290, 'Job Destruction']

Index([111, 169], dtype='int64')

regionjob1=regionjob.pivot_table(values=['Auckland'], index=['Type'], columns='Year')
regionjob1

years = regionjob1.columns.levels[1].tolist()  
job_creation = regionjob1.loc['Job Creation'].values.flatten().tolist() 
job_destruction = regionjob1.loc['Job Destruction'].values.flatten().tolist()  

plt.figure(figsize=(12, 6))
plt.plot(years, job_creation, label='Job Creation', marker='o')
plt.plot(years, job_destruction, label='Job Destruction', marker='x')

plt.title('Job Creation and Destruction in Auckland from 1999 to 2022')
plt.xlabel('Year')
plt.ylabel('Number of Jobs')
plt.xticks(years, rotation=45)  
plt.legend()

<matplotlib.legend.Legend at 0x2ca66e42050>

df_jobprofiles

grouped = df_jobprofiles.groupby(['Job Opportunities','Industry'])
grouped.groups

{('Average', 'Construction and infrastructure'): [130, 175, 176, 200], ('Average', 'Construction and infrastructure, Creative industries'): [187], ('Average', 'Construction and infrastructure, Manufacturing and technology'): [136, 174, 258], ('Average', 'Construction and infrastructure, Manufacturing and technology, Creative industries'): [282, 283], ('Average', 'Construction and infrastructure, Primary industries'): [254], ('Average', 'Construction and infrastructure, Primary industries, Creative industries'): [182], ('Average', 'Construction and infrastructure, Services industries'): [0, 327], ('Average', 'Construction and infrastructure, Services industries, Manufacturing and technology'): [54], ('Average', 'Creative industries'): [51, 297, 330], ('Average', 'Manufacturing and technology'): [16, 48, 213, 215, 357], ('Average', 'Manufacturing and technology, Construction and infrastructure'): [251], ('Average', 'Manufacturing and technology, Creative industries'): [49, 346, 347, 348, 408], ('Average', 'Manufacturing and technology, Primary industries'): [312, 402, 412], ('Average', 'Manufacturing and technology, Services industries'): [77], ('Average', 'Manufacturing and technology, Services industries, Creative industries'): [244, 354], ('Average', 'Primary industries'): [19, 88, 109, 110, 139, 305, 338, 396, 414], ('Average', 'Primary industries, Services industries'): [21, 307, 355], ('Average', 'Primary industries, Social and community services'): [157], ('Average', 'Services industries'): [8, 22, 44, 53, 81, 93, 153, 180, 204, 207, 209, 229, 239, 252, 253, 284, 285, 314, 316, 319, 328, 332, 333, 334, 353, 363, 364, 371, 373, 387, 388, 389, 390, 403], ('Average', 'Services industries, Creative industries'): [80, 238, 294, 299, 308, 350, 397, 400], ('Average', 'Services industries, Manufacturing and technology'): [64, 318], ('Average', 'Services industries, Primary industries'): [181], ('Average', 'Services industries, Social and community services'): [105, 106, 108, 205, 303], ('Average', 'Social and community services'): [34, 103, 104, 113, 135, 140, 141, 142, 144, 149, 161, 196, 234, 237, 265, 280, 291, 367, 377], ('Average', 'Social and community services, Primary industries'): [191, 250], ('Average', 'Social and community services, Services industries'): [73], ('Average', 'Social and community services, Services industries, Primary industries'): [409], ('Good', 'Construction and infrastructure'): [2, 32, 36, 37, 45, 46, 50, 55, 62, 65, 134, 162, 163, 165, 202, 208, 220, 230, 231, 376, 405], ('Good', 'Construction and infrastructure, Creative industries'): [129, 255], ('Good', 'Construction and infrastructure, Manufacturing and technology'): [59, 128, 262, 289, 374, 375, 401], ('Good', 'Construction and infrastructure, Primary industries'): [232], ('Good', 'Construction and infrastructure, Primary industries, Manufacturing and technology'): [78], ('Good', 'Construction and infrastructure, Services industries'): [190], ('Good', 'Construction and infrastructure, Services industries, Manufacturing and technology'): [124], ('Good', 'Construction and infrastructure, Social and community services'): [186], ('Good', 'Manufacturing and technology'): [4, 23, 28, 47, 60, 66, 75, 76, 91, 95, 117, 119, 123, 127, 132, 133, 160, 272, 273, 275, 276, 277, 278, 279, 287, 288, 290, 302, 342, 345, 362, 379, 380, 407], ('Good', 'Manufacturing and technology, Construction and infrastructure'): [164, 222, 320], ('Good', 'Manufacturing and technology, Creative industries'): [349], ('Good', 'Manufacturing and technology, Primary industries'): [5, 96, 216, 313, 398], ('Good', 'Manufacturing and technology, Services industries'): [26, 94, 126, 211, 263, 321, 341], ('Good', 'Manufacturing and technology, Social and community services'): [292], ('Good', 'Primary industries'): [9, 13, 17, 20, 61, 111, 112, 152, 171, 172, 177, 178, 206, 214, 322, 323, 324, 337, 344, 368, 404], ('Good', 'Primary industries, Construction and infrastructure'): [52], ('Good', 'Primary industries, Manufacturing and technology'): [370], ('Good', 'Primary industries, Social and community services'): [31], ('Good', 'Services industries'): [6, 7, 24, 35, 38, 40, 42, 58, 63, 69, 70, 71, 74, 82, 89, 90, 97, 99, 100, 118, 166, 168, 169, 170, 179, 183, 194, 199, 217, 218, 223, 249, 256, 267, 300, 301, 309, 310, 311, 315, 329, 336, 356, 369, 381, 382, 391, 392, 399], ('Good', 'Services industries, Construction and infrastructure'): [351], ('Good', 'Services industries, Creative industries'): [79, 138, 335, 361], ('Good', 'Services industries, Manufacturing and technology'): [359], ('Good', 'Services industries, Social and community services'): [10, 107, 221, 264, 281, 304, 395], ('Good', 'Services industries, Social and community services, Primary industries'): [120, 167], ('Good', 'Social and community services'): [18, 30, 68, 83, 86, 92, 98, 101, 102, 116, 121, 122, 125, 131, 137, 143, 145, 146, 148, 154, 155, 156, 158, 159, 185, 192, 195, 201, 203, 224, 226, 227, 235, 240, 245, 247, 259, 261, 270, 271, 274, 306, 317, 325, 326, 331, 366, 383, 411], ('Good', 'Social and community services, Manufacturing and technology'): [84, 233], ('Good', 'Social and community services, Primary industries'): [413], ('Good', 'Social and community services, Services industries'): [147, 150], ('Poor', 'Construction and infrastructure'): [173], ('Poor', 'Construction and infrastructure, Manufacturing and technology'): [56], ('Poor', 'Creative industries'): [1, 11, 12, 14, 188, 197, 198, 210, 219, 241, 243, 260, 295, 298, 358, 385, 394], ('Poor', 'Manufacturing and technology'): [39, 212, 257, 384], ('Poor', 'Manufacturing and technology, Creative industries'): [286, 296, 340], ('Poor', 'Manufacturing and technology, Primary industries'): [386], ('Poor', 'Manufacturing and technology, Services industries'): [33], ('Poor', 'Manufacturing and technology, Social and community services'): [184], ('Poor', 'Primary industries, Services industries'): [416], ('Poor', 'Primary industries, Social and community services'): [151], ('Poor', 'Services industries'): [3, 25, 43, 85, 87, 228, 236, 246, 293, 339, 365, 372, 378, 393, 406, 410], ('Poor', 'Services industries, Construction and infrastructure'): [189], ('Poor', 'Services industries, Creative industries'): [41, 57, 193, 242, 343, 352, 360], ('Poor', 'Services industries, Social and community services'): [114, 268], ('Poor', 'Social and community services'): [15, 27, 67, 72, 225, 248, 266, 269, 415], ('Poor', 'Social and community services, Services industries, Creative industries'): [29, 115]}

df_jobprofiles1=df_jobprofiles.iloc[grouped.groups['Good', 'Manufacturing and technology']]
df_jobprofiles1

df = pd.DataFrame(df_jobprofiles1)

def split_earnings(earnings):
    earnings = earnings.replace("K", "000").replace("per hour", "").replace("per year", "").replace("$", "").strip()
    earnings = earnings.replace("−", "-") 
    try:
        if "," in earnings:
            parts = earnings.split(",")
            min_earning = float(parts[0].split("-")[0].strip())
            max_earning = float(parts[1].split("-")[1].strip())
        elif "-" in earnings:
            parts = earnings.split("-")
            min_earning = float(parts[0].strip())
            max_earning = float(parts[1].strip())
        else:
            min_earning = max_earning = float(earnings.strip())
    except Exception as e:
        print(f"Error processing earnings '{earnings}': {e}")
        min_earning = max_earning = None
    return min_earning, max_earning

df[['Min Earnings', 'Max Earnings']] = df['Earnings'].apply(split_earnings).apply(pd.Series)
df

Error processing earnings '115000–140000 , 145000–160000': could not convert string to float: '115000–140000'

df = pd.DataFrame(df_jobprofiles1)

def split_earnings(earnings):
    earnings = earnings.replace("K", "000").replace("per hour", "").replace("per year", "").replace("$", "").strip()
    earnings = earnings.replace("−", "-")  
    try:
        if "," in earnings:
            parts = earnings.split(",")
            min_earning = float(parts[0].split("-")[0].strip())
            max_earning = float(parts[1].split("-")[1].strip())
        elif "-" in earnings:
            parts = earnings.split("-")
            min_earning = float(parts[0].strip())
            max_earning = float(parts[1].strip())
        else:
            min_earning = max_earning = float(earnings.strip())
    except Exception as e:
        print(f"Error processing earnings '{earnings}': {e}")
        min_earning = max_earning = None
    return min_earning, max_earning

df[['Min Earnings', 'Max Earnings']] = df['Earnings'].apply(split_earnings).apply(pd.Series)
df_filtered = df[df['Max Earnings'] >= 5000]

plt.figure(figsize=(10, 6))
plt.barh(df_filtered['Occupation'], df_filtered['Max Earnings'], color='fuchsia')
plt.xlabel('Maximum Earnings')
plt.ylabel('Occupation')
plt.title('Maximum Earnings by Occupation (Yearly Salary) ')

Error processing earnings '115000–140000 , 145000–160000': could not convert string to float: '115000–140000'

Text(0.5, 1.0, 'Maximum Earnings by Occupation (Yearly Salary) ')

df = pd.DataFrame(df_jobprofiles1)

def split_earnings(earnings):
    earnings = earnings.replace("K", "000").replace("per hour", "").replace("per year", "").replace("$", "").strip()
    earnings = earnings.replace("−", "-") 
    try:
        if "," in earnings:
            parts = earnings.split(",")
            min_earning = float(parts[0].split("-")[0].strip())
            max_earning = float(parts[1].split("-")[1].strip())
        elif "-" in earnings:
            parts = earnings.split("-")
            min_earning = float(parts[0].strip())
            max_earning = float(parts[1].strip())
        else:
            min_earning = max_earning = float(earnings.strip())
    except Exception as e:
        print(f"Error processing earnings '{earnings}': {e}")
        min_earning = max_earning = None
    return min_earning, max_earning

df[['Min Earnings', 'Max Earnings']] = df['Earnings'].apply(split_earnings).apply(pd.Series)

df_filtered = df[df['Max Earnings'] >= 5000]

df_sorted = df_filtered.sort_values(by='Max Earnings', ascending=False)

plt.figure(figsize=(10, 6))
plt.barh(df_sorted['Training Required'], df_sorted['Max Earnings'], color='indigo')
plt.xlabel('Maximum Earnings')
plt.ylabel('Training Required')
plt.title('Maximum Earnings by Training Required (Yearly Salary) ')

Error processing earnings '115000–140000 , 145000–160000': could not convert string to float: '115000–140000'

Text(0.5, 1.0, 'Maximum Earnings by Training Required (Yearly Salary) ')

	industry_short	value_base	value_focus
0	total	367582.4	377783.6
1	agriculture, forestry, fishing	18182.6	18731.6
2	mining	3052.9	2836.7
3	manufacturing	32875.9	30887.4
4	electricity, gas, water, waste	9739.0	9999.9

	Industry	GDP_2022(M)	GDP_2023(M)
1	agriculture, forestry, fishing	18182.6	18731.6
2	mining	3052.9	2836.7
3	manufacturing	32875.9	30887.4
4	electricity, gas, water, waste	9739.0	9999.9
5	construction	23404.8	23905.0

	Industry	Employment_2022	Employment_2023	GDP_2022(M)	GDP_2023(M)
0	agriculture, forestry, fishing	147044.0	145796.0	18182.6	18731.6
1	mining	5932.0	6162.0	3052.9	2836.7
2	manufacturing	246399.0	251850.0	32875.9	30887.4
3	electricity, gas, water, waste	19816.0	20951.0	9739.0	9999.9
4	construction	278338.0	287652.0	23404.8	23905.0

	Title	Sub Title	Description	Job Opportunities	Training Required	Vocations	Earnings
0	Energy/Carbon Auditor	Kaitātari Pūngao/Waro	Energy/carbon auditors assess the amount of en...	Average	2-3 years	Construction and infrastructure, Services indu...	$60K-$ 80K per year, $80K-$ 200K per year
1	Television Presenter	Kaipānui Pouaka Whakaata	Television presenters introduce, present or ho...	Poor	N/A	Creative industries
2	Facilities Manager	Kaiwhakahaere Whakaurunga	Facilities managers co-ordinate the strategic ...	Good	N/A	Construction and infrastructure	$55K-$ 100K per year, $100K-$ 150K per year
3	Aircraft Refueller	Kaiwhakakī Waka Rererangi	Aircraft refuellers fill aircraft with fuel at...	Poor	<1 year	Services industries	$55K-$ 65K per year, $65K-$ 75K per year
4	Electronics Engineer	Mataaro Tāhiko	Electronics engineers design and oversee produ...	Good	4 years	Manufacturing and technology	$100K per year

	Missing Values Count	Missing Percentage
0	36	100.000000
1	36	100.000000
2	35	97.222222
3	35	97.222222
4	35	97.222222
5	35	97.222222
6	35	97.222222
7	0	0.000000
8	0	0.000000
9	0	0.000000
10	0	0.000000
11	0	0.000000
12	0	0.000000
13	0	0.000000
14	0	0.000000
15	0	0.000000
16	0	0.000000
17	0	0.000000
18	0	0.000000
19	0	0.000000
20	0	0.000000
21	0	0.000000
22	0	0.000000
23	0	0.000000
24	0	0.000000
25	0	0.000000
26	0	0.000000
27	0	0.000000
28	0	0.000000
29	0	0.000000
30	0	0.000000
31	0	0.000000
32	0	0.000000
33	0	0.000000
34	0	0.000000
35	0	0.000000
36	0	0.000000
37	0	0.000000
38	0	0.000000
39	0	0.000000
40	0	0.000000
41	0	0.000000
42	0	0.000000
43	0	0.000000
44	0	0.000000
45	0	0.000000
46	0	0.000000
47	0	0.000000
48	0	0.000000
49	0	0.000000
50	0	0.000000
51	0	0.000000
52	0	0.000000
53	0	0.000000
54	0	0.000000
55	0	0.000000
56	0	0.000000
57	0	0.000000
58	0	0.000000
59	0	0.000000
60	0	0.000000

	change_contribution	change	change_total_val	area_name	year_base	year_focus	value_base	value_focus	area_id	area_type	...	industry_type_code	industry	industry_short	industry_description	percent_total	parent_industry_code	parents	key	industry_types.industry_type_code	industry_types.name
0	2.80	2.8	10201.2	New Zealand	2022	2023	367582.4	377783.6	new-zealand	NZ	...	TOTAL	total economy	total	For data not broken down by industry	NaN	NaN	NaN	NaN	NaN	gross domestic product
1	0.15	3.0	549.0	New Zealand	2022	2023	18182.6	18731.6	new-zealand	NZ	...	L1	agriculture, forestry and fishing	agriculture, forestry, fishing	Includes: growing crops, raising animals, grow...	4.96	TOTAL	[{'industry_type_code': 'TOTAL', 'industry_cod...	NaN	NaN	gross domestic product
2	-0.06	-7.1	-216.2	New Zealand	2022	2023	3052.9	2836.7	new-zealand	NZ	...	L1	mining	mining	Includes: extraction of naturally occurring mi...	0.75	TOTAL	[{'industry_type_code': 'TOTAL', 'industry_cod...	NaN	NaN	gross domestic product
3	-0.55	-6.0	-1988.5	New Zealand	2022	2023	32875.9	30887.4	new-zealand	NZ	...	L1	manufacturing	manufacturing	Includes: physical or chemical transformation ...	8.18	TOTAL	[{'industry_type_code': 'TOTAL', 'industry_cod...	NaN	NaN	gross domestic product
4	0.07	2.7	260.9	New Zealand	2022	2023	9739.0	9999.9	new-zealand	NZ	...	L1	electricity, gas, water and waste services	electricity, gas, water, waste	Includes: provision of electricity, gas throug...	2.65	TOTAL	[{'industry_type_code': 'TOTAL', 'industry_cod...	NaN	NaN	gross domestic product

	percent_total	industry_type_code	industry_code	industry	industry_short	industry_description	change_contribution	change	change_total_val	area_name	year_base	year_focus	value_base	value_focus	area_id	area_type	sort_order	key	industry_types.industry_type_code	industry_types.name
0	5.29	L1	A	agriculture, forestry and fishing	agriculture, forestry, fishing	Includes: growing crops, raising animals, grow...	-0.05	-0.8	-1248.0	New Zealand	2022	2023	147044.0	145796.0	new-zealand	NZ	9999	NaN	NaN	employment
1	0.22	L1	B	mining	mining	Includes: extraction of naturally occurring mi...	0.01	3.9	230.0	New Zealand	2022	2023	5932.0	6162.0	new-zealand	NZ	9999	NaN	NaN	employment
2	9.15	L1	C	manufacturing	manufacturing	Includes: physical or chemical transformation ...	0.21	2.2	5451.0	New Zealand	2022	2023	246399.0	251850.0	new-zealand	NZ	9999	NaN	NaN	employment
3	0.76	L1	D	electricity, gas, water and waste services	electricity, gas, water, waste	Includes: provision of electricity, gas throug...	0.04	5.7	1135.0	New Zealand	2022	2023	19816.0	20951.0	new-zealand	NZ	9999	NaN	NaN	employment
4	10.45	L1	E	construction	construction	Includes: construction of buildings and other ...	0.35	3.3	9314.0	New Zealand	2022	2023	278338.0	287652.0	new-zealand	NZ	9999	NaN	NaN	employment

	Title	Sub Title	Description	Job Opportunities	Training Required	Vocations	Earnings
count	417	417	417	417	417	417	417
unique	417	414	417	3	39	36	318
top	Energy/Carbon Auditor	Ringawera	Energy/carbon auditors assess the amount of en...	Good	N/A	Services industries
freq	1	2	1	228	146	99	26

	Date	Auckland	Bay of Plenty	Canterbury	Gisborne Hawke's Bay	Marlborough/NelsonTasman/West Coast	Manawatu/Wanganui-Taranaki	Northland	Otago Southland	Waikato	...	OCCUPATION
	Unnamed: 0_level_1	Unnamed: 1_level_1	Unnamed: 2_level_1	Unnamed: 3_level_1	Unnamed: 4_level_1	Unnamed: 5_level_1	Unnamed: 6_level_1	Unnamed: 7_level_1	Unnamed: 8_level_1	Unnamed: 9_level_1	...	Sales	Machinery Drivers	Labourers	highly skilled	skilled	semi-skilled	low skilled	unskilled	Skilled	Unskilled
0	NaT	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
1	NaT	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2	2009-09-01	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
3	2009-12-01	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
4	2010-03-01	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN

	Date	Auckland	Bay of Plenty	Canterbury	Gisborne Hawke's Bay	Marlborough/NelsonTasman/West Coast	Manawatu/Wanganui-Taranaki	Northland	Otago Southland	Waikato	Wellington	ids_Accounting	ids_Construction	ids_Education	ids_Health	ids_Hospitalty	ids_IT	ids_Manufacturing	ids_Primary	ids_Sales	ids_Other	ocp_Managers	ocp_Professionals	ocp_Tech & Trades	ocp_Community & Personal Services	ocp_Clerical & Administration	ocp_Sales	ocp_Machinery Drivers	ocp_Labourers	ocp_highly skilled	ocp_skilled	ocp_semi-skilled	ocp_low skilled	ocp_unskilled	ocp_Skilled	ocp_Unskilled
7	2010-12-01	100.000	100.000	100.000	100.000	100.000	100.000	100.000	100.000	100.000	100.000	100.000	100.000	100.000	100.000	100.000	100.000	100.000	100.000	100.000	100.000	100.000	100.000	100.000	100.000	100.000	100.000	100.000	100.000	100.000	100.000	100.000	100.000	100.000	100.000	100.000
8	2011-03-01	101.457	101.561	107.036	103.535	102.370	100.780	103.643	106.457	102.388	101.849	101.830	107.252	96.481	98.957	104.711	101.374	103.521	108.968	100.481	102.091	101.755	102.361	110.413	107.814	101.682	104.106	102.947	109.816	102.438	101.859	113.548	105.121	102.011	104.132	104.480
9	2011-06-01	101.942	102.781	129.833	106.559	105.940	102.055	108.489	111.892	105.167	102.005	105.035	114.110	92.110	101.100	108.760	102.307	109.045	118.109	101.360	106.037	103.000	105.634	119.675	114.379	105.660	107.007	109.098	116.151	105.300	102.154	125.963	110.445	103.550	107.945	109.077
10	2011-09-01	101.542	104.443	139.557	109.635	114.017	104.820	113.102	119.014	107.132	100.886	108.501	118.782	91.165	105.883	108.103	102.536	115.264	129.535	102.664	112.256	104.741	108.902	125.667	117.779	110.105	106.261	117.874	120.426	107.653	104.015	132.978	113.728	104.835	110.780	112.078
11	2011-12-01	101.208	106.354	150.820	111.782	122.670	108.420	112.774	126.815	107.699	100.552	109.625	122.864	89.039	111.135	107.003	102.640	117.823	138.805	103.434	115.405	106.173	109.886	128.853	121.391	111.857	103.751	123.715	126.862	108.200	106.747	135.339	114.841	107.073	111.802	113.392

	Date	Type	Auckland	Waikato	Bay of Plenty	Gisborne	Hawke's Bay	Taranaki	Manawatu-Wanganui	Wellington	Tasman, Nelson, Marlborough, West Coast	Canterbury	Otago
0	1999Q2	Job Creation	41890	5570	3430	520	2040	1560	3480	20430	1900	9430	3070
1	1999Q3	Job Creation	2710	340	370	35	120	90	170	1080	130	670	170
2	1999Q4	Job Creation	3040	500	260	30	150	120	220	1100	100	820	220
3	2000Q1	Job Creation	3340	610	420	45	210	210	240	1530	130	750	210
4	2000Q2	Job Creation	3700	760	400	25	210	180	260	1820	150	1140	380

	Auckland	Waikato	Bay of Plenty	Gisborne	Hawke's Bay	Taranaki	Manawatu-Wanganui	Wellington	Tasman, Nelson, Marlborough, West Coast	Canterbury	Otago
count	190.000000	190.000000	190.000000	190.000000	190.000000	190.000000	190.000000	190.000000	190.000000	190.000000	190.000000
mean	4237.473684	614.368421	453.263158	55.221053	214.131579	150.921053	250.315789	1511.000000	208.473684	1066.684211	327.736842
std	2954.425062	405.542776	277.856276	41.516537	148.068369	110.653753	245.363148	1433.490412	138.220118	697.969129	222.624162
min	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000
25%	3307.500000	462.500000	320.000000	35.000000	160.000000	110.000000	190.000000	1110.000000	160.000000	782.500000	250.000000
50%	3930.000000	560.000000	400.000000	50.000000	200.000000	140.000000	220.000000	1400.000000	190.000000	965.000000	300.000000
75%	4727.500000	690.000000	497.500000	65.000000	230.000000	170.000000	260.000000	1617.500000	237.500000	1200.000000	380.000000
max	41890.000000	5570.000000	3430.000000	520.000000	2040.000000	1560.000000	3480.000000	20430.000000	1900.000000	9430.000000	3070.000000

	Year	Type	Auckland	Waikato	Bay of Plenty	Gisborne	Hawke's Bay	Taranaki	Manawatu-Wanganui	Wellington	Tasman, Nelson, Marlborough, West Coast	Canterbury	Otago
0	1999	Job Creation	5750	840	630	65	270	210	390	2180	230	1490	390
1	1999	Job Destruction	4510	720	430	60	275	145	300	2130	165	990	570
2	2000	Job Creation	13440	2210	1420	150	880	630	970	6050	540	3290	980
3	2000	Job Destruction	13200	1800	1130	145	750	540	930	5350	510	3040	1070
4	2001	Job Creation	15100	2190	1350	165	810	600	850	6820	590	4580	1000

		Auckland	Bay of Plenty	Canterbury	Gisborne	Hawke's Bay	Manawatu-Wanganui	Otago	Taranaki	Tasman, Nelson, Marlborough, West Coast	Waikato	Wellington
Type	Year
Job Creation	1999	5750	630	1490	65	270	390	390	210	230	840	2180
	2000	13440	1420	3290	150	880	970	980	630	540	2210	6050
	2001	15100	1350	4580	165	810	850	1000	600	590	2190	6820
	2002	14720	1680	2940	190	1170	850	840	620	620	2080	5810
	2003	14590	1940	3270	150	820	1040	1140	710	710	2220	4830

	Year	Not in Labour Force	Working Age Population	Labour Force Participation Rate	Unemployment Rate	Employment Rate	Total Labour Force
0	1986	..	..	..	..	..	..
1	1987	545.5	2205.3	75.3	4.2	72.1	1659.8
2	1988	557.1	2221.2	74.9	4.5	71.6	1664
3	1989	592.9	2229.4	73.4	6.4	68.7	1636.5
4	1990	616.8	2236.9	72.4	7.4	67.1	1620.2

	Date	15-19	20-24	25-29	30-34	35-39	40-44	45-49	50-54	55-59	60-64	65	Total All Ages
0	1999Q2	1610	5650	7530	8050	7930	7800	7920	7800	7380	6630	2390	7020
1	1999Q3	1600	5870	7860	8400	8240	8080	8210	8040	7590	6790	2510	7300
2	1999Q4	2140	6320	8300	8960	8900	8750	8790	8600	8140	7360	2930	7870
3	2000Q1	2210	5810	7640	8230	8170	8030	8090	7910	7480	6750	2700	7230
4	2000Q2	1810	5970	7880	8450	8300	8150	8260	8110	7650	6950	2710	7390

	Year	15-19	20-24	25-29	30-34	35-39	40-44	45-49	50-54	55-59	60-64	65	Total All Ages
0	1999	1783.3	5946.7	7896.7	8470.0	8356.7	8210.0	8306.7	8146.7	7703.3	6926.7	2610.0	7396.7
1	2000	2017.5	6042.5	7960.0	8575.0	8477.5	8317.5	8390.0	8230.0	7757.5	7035.0	2845.0	7512.5
2	2001	2190.0	6190.0	8165.0	8825.0	8755.0	8602.5	8650.0	8507.5	8032.5	7262.5	3282.5	7745.0
3	2002	2355.0	6370.0	8392.5	9107.5	9067.5	8947.5	8945.0	8837.5	8385.0	7567.5	3675.0	8002.5
4	2003	2505.0	6522.5	8620.0	9397.5	9372.5	9270.0	9275.0	9167.5	8727.5	7900.0	4090.0	8260.0

	Year	Northland	Auckland	Waikato	Bay of Plenty	Gisborne	Hawke's Bay	Taranaki	Manawatu-Whanganui	Wellington	West Coast	Canterbury	Otago	Southland	Marlborough	Tasman/Nelson	Total North Island	Total South Island	New Zealand
0	2000	2655	37716	8582	5430	901	3386	3595	4742	16021	647	12215	4265	2355	935	1900	83028	22317	105345
1	2001	2954	38850	9712	5843	945	3643	4378	5065	16250	734	12849	4606	2746	1025	2035	87640	23995	111635
2	2002	3188	41840	10595	6238	986	3882	4479	5421	17424	773	13795	5030	2966	1135	2219	94054	25919	119973
3	2003	3082	45772	10181	6405	1008	4090	4344	5434	18184	744	14675	5347	2882	1160	2300	98500	27108	125607
4	2004	3316	49398	11038	6810	1020	4368	4327	5782	19021	818	15851	5732	2994	1276	2481	105079	29152	134231
5	2005	3659	53230	11666	7297	1073	4690	4356	6144	19957	862	17328	6198	2972	1351	2661	112073	31372	143444
6	2006	3969	55823	12516	7664	1087	4814	4518	6590	21190	1002	18272	6463	3163	1429	2653	118170	32982	151152
7	2007	4345	57384	13869	8399	1170	4946	5287	6695	21615	1075	19368	6807	3373	1584	2864	123709	35070	158779
8	2008	4619	61743	14708	9110	1211	4854	7649	7245	23220	1260	20901	7322	3873	1802	3047	134359	38204	172564
9	2009	4734	61098	15526	9039	1285	5061	7924	7165	23816	1388	21611	7577	4123	1851	3166	135648	39715	175363
10	2010	4543	63382	15258	9409	1324	5150	7665	7544	25113	1351	22229	7894	4168	1794	3296	139388	40731	180119
11	2011	4842	65759	16075	9947	1394	5447	7977	7888	25501	1427	23219	8171	4498	1813	3446	144830	42574	187404
12	2012	4922	68978	17102	10321	1432	5575	7896	7997	26724	1517	24316	8402	4599	1919	3503	150947	44256	195203
13	2013	4899	71351	16725	10490	1427	5730	7967	7999	27149	1449	25371	8526	4432	2001	3581	153739	45360	199099
14	2014	5363	75444	18690	11030	1474	6044	8508	8558	28348	1548	28198	9224	5075	2224	3873	163457	50143	213600
15	2015	5555	81076	18754	11291	1541	6176	8329	8681	29588	1479	29434	9427	4841	2338	3996	170990	51516	222506
16	2016	5994	88139	19413	12287	1638	6444	7221	8944	30654	1380	30338	10057	4693	2440	4216	180735	53124	233859
17	2017	6428	93624	20709	13820	1707	7011	7279	9358	32240	1450	31189	10745	5122	2604	4492	192176	55602	247778
18	2018	6970	99794	22583	15106	1844	7567	8129	10123	33610	1632	33555	11754	5609	2798	4835	205727	60184	265911
19	2019	7238	105433	24349	16322	1999	7886	8245	10744	34849	1685	35066	12484	5932	2966	5162	217065	63295	280360
20	2020	7712	110312	25993	17283	2056	8397	8483	11344	37561	1725	37099	13097	6093	3135	5487	229139	66638	295777
21	2021	7804	113290	26954	18012	2256	8878	8077	12115	37606	1784	37011	12860	6180	3197	5582	234991	66613	301604
22	2022	8684	124270	29378	19527	2318	9773	8911	13110	40777	1798	40380	14016	7144	3283	6038	256748	72659	329407
23	2023	..	..	..	..	..	..	..	..	..	..	..	..	..	..	..	..	..	..

	Year	Northland	Auckland	Waikato	Bay of Plenty	Gisborne	Hawke's Bay	Taranaki	Manawatu-Whanganui	Wellington	West Coast	Canterbury	Otago	Southland	Marlborough	Tasman/Nelson	Total North Island	Total South Island	New Zealand
0	2000	2655.0	37716.0	8582.0	5430.0	901.0	3386.0	3595.0	4742.0	16021.0	647.0	12215.0	4265.0	2355.0	935.0	1900.0	83028.0	22317.0	105345.0
1	2001	2954.0	38850.0	9712.0	5843.0	945.0	3643.0	4378.0	5065.0	16250.0	734.0	12849.0	4606.0	2746.0	1025.0	2035.0	87640.0	23995.0	111635.0
2	2002	3188.0	41840.0	10595.0	6238.0	986.0	3882.0	4479.0	5421.0	17424.0	773.0	13795.0	5030.0	2966.0	1135.0	2219.0	94054.0	25919.0	119973.0
3	2003	3082.0	45772.0	10181.0	6405.0	1008.0	4090.0	4344.0	5434.0	18184.0	744.0	14675.0	5347.0	2882.0	1160.0	2300.0	98500.0	27108.0	125607.0
4	2004	3316.0	49398.0	11038.0	6810.0	1020.0	4368.0	4327.0	5782.0	19021.0	818.0	15851.0	5732.0	2994.0	1276.0	2481.0	105079.0	29152.0	134231.0
5	2005	3659.0	53230.0	11666.0	7297.0	1073.0	4690.0	4356.0	6144.0	19957.0	862.0	17328.0	6198.0	2972.0	1351.0	2661.0	112073.0	31372.0	143444.0
6	2006	3969.0	55823.0	12516.0	7664.0	1087.0	4814.0	4518.0	6590.0	21190.0	1002.0	18272.0	6463.0	3163.0	1429.0	2653.0	118170.0	32982.0	151152.0
7	2007	4345.0	57384.0	13869.0	8399.0	1170.0	4946.0	5287.0	6695.0	21615.0	1075.0	19368.0	6807.0	3373.0	1584.0	2864.0	123709.0	35070.0	158779.0
8	2008	4619.0	61743.0	14708.0	9110.0	1211.0	4854.0	7649.0	7245.0	23220.0	1260.0	20901.0	7322.0	3873.0	1802.0	3047.0	134359.0	38204.0	172564.0
9	2009	4734.0	61098.0	15526.0	9039.0	1285.0	5061.0	7924.0	7165.0	23816.0	1388.0	21611.0	7577.0	4123.0	1851.0	3166.0	135648.0	39715.0	175363.0
10	2010	4543.0	63382.0	15258.0	9409.0	1324.0	5150.0	7665.0	7544.0	25113.0	1351.0	22229.0	7894.0	4168.0	1794.0	3296.0	139388.0	40731.0	180119.0
11	2011	4842.0	65759.0	16075.0	9947.0	1394.0	5447.0	7977.0	7888.0	25501.0	1427.0	23219.0	8171.0	4498.0	1813.0	3446.0	144830.0	42574.0	187404.0
12	2012	4922.0	68978.0	17102.0	10321.0	1432.0	5575.0	7896.0	7997.0	26724.0	1517.0	24316.0	8402.0	4599.0	1919.0	3503.0	150947.0	44256.0	195203.0
13	2013	4899.0	71351.0	16725.0	10490.0	1427.0	5730.0	7967.0	7999.0	27149.0	1449.0	25371.0	8526.0	4432.0	2001.0	3581.0	153739.0	45360.0	199099.0
14	2014	5363.0	75444.0	18690.0	11030.0	1474.0	6044.0	8508.0	8558.0	28348.0	1548.0	28198.0	9224.0	5075.0	2224.0	3873.0	163457.0	50143.0	213600.0
15	2015	5555.0	81076.0	18754.0	11291.0	1541.0	6176.0	8329.0	8681.0	29588.0	1479.0	29434.0	9427.0	4841.0	2338.0	3996.0	170990.0	51516.0	222506.0
16	2016	5994.0	88139.0	19413.0	12287.0	1638.0	6444.0	7221.0	8944.0	30654.0	1380.0	30338.0	10057.0	4693.0	2440.0	4216.0	180735.0	53124.0	233859.0
17	2017	6428.0	93624.0	20709.0	13820.0	1707.0	7011.0	7279.0	9358.0	32240.0	1450.0	31189.0	10745.0	5122.0	2604.0	4492.0	192176.0	55602.0	247778.0
18	2018	6970.0	99794.0	22583.0	15106.0	1844.0	7567.0	8129.0	10123.0	33610.0	1632.0	33555.0	11754.0	5609.0	2798.0	4835.0	205727.0	60184.0	265911.0
19	2019	7238.0	105433.0	24349.0	16322.0	1999.0	7886.0	8245.0	10744.0	34849.0	1685.0	35066.0	12484.0	5932.0	2966.0	5162.0	217065.0	63295.0	280360.0
20	2020	7712.0	110312.0	25993.0	17283.0	2056.0	8397.0	8483.0	11344.0	37561.0	1725.0	37099.0	13097.0	6093.0	3135.0	5487.0	229139.0	66638.0	295777.0
21	2021	7804.0	113290.0	26954.0	18012.0	2256.0	8878.0	8077.0	12115.0	37606.0	1784.0	37011.0	12860.0	6180.0	3197.0	5582.0	234991.0	66613.0	301604.0
22	2022	8684.0	124270.0	29378.0	19527.0	2318.0	9773.0	8911.0	13110.0	40777.0	1798.0	40380.0	14016.0	7144.0	3283.0	6038.0	256748.0	72659.0	329407.0
23	2023	9663.2	136314.2	32020.0	21169.4	2381.7	10758.2	9831.1	14186.7	44215.4	1812.1	44055.7	15275.9	8258.4	3371.3	6531.3	280519.4	79253.8	359773.0

	Year
count	39.000000
mean	2005.000000
std	11.401754
min	1986.000000
25%	1995.500000
50%	2005.000000
75%	2014.500000
max	2024.000000

	Year	Agriculture	Forestry, Fishing, and Mining	Forestry, Fishing, Mining, Electricity, Gas, Water and Waste Services	Primary Manufacturing	Other Manufacturing	Manufacturing	Electricity, Gas, Water, and Waste services	Construction	Wholesale Trade	Retail Trade	Accommodation and Food Services	Accommodation	Food and beverage services	Transport, Postal and Warehousing	Information Media, Telecommunications and Other Services	Financial and Insurance Services	Rental, Hiring and Real Estate Services	Owner-Occupied Property Operation	Professional, Scientific, and Technical Services	Administrative and Support Services	Public Administration and Safety	Education and Training	Health Care and Social Assistance	Total All Industries
0	2000	5165	3138	6388	11156	6458	17614	3250	5179	6211	5086	2086.0	701	1386	5274	8460	4956	6355	8416	7594	2064	4313	4838	5344	105345
1	2001	7124	3549	6718	12070	6510	18580	3169	5139	6621	5346	2317.0	810	1506	5297	8924	5390	6711	8522	7596	2067	4505	5066	5711	111635
2	2002	8048	3648	6935	12513	7038	19551	3287	5484	7433	6130	2521.0	891	1630	5612	9539	5906	7187	8707	8426	2321	4794	5207	6171	119973
3	2003	5750	3639	7337	13618	7405	21023	3698	6053	7259	6826	2477.0	851	1626	6129	10420	6430	7856	9221	9095	2553	5039	5553	6586	125607
4	2004	6251	3352	7562	13378	7890	21268	4210	6806	7932	7202	2832.0	978	1854	6586	11070	7289	8641	9840	9672	2733	5310	6044	7195	134231

	Year	Auckland	Bay of Plenty	Canterbury	Gisborne Hawke's Bay	Marlborough/NelsonTasman/West Coast	Manawatu/Wanganui-Taranaki	Northland	Otago Southland	Waikato	Wellington	ids_Accounting	ids_Construction	ids_Education	ids_Health	ids_Hospitalty	ids_IT	ids_Manufacturing	ids_Primary	ids_Sales	ids_Other	ocp_Managers	ocp_Professionals	ocp_Tech & Trades	ocp_Community & Personal Services	ocp_Clerical & Administration	ocp_Sales	ocp_Machinery Drivers	ocp_Labourers	ocp_highly skilled	ocp_skilled	ocp_semi-skilled	ocp_low skilled	ocp_unskilled	ocp_Skilled	ocp_Unskilled
0	2010	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000	100.0000	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000	100.0000	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000
1	2011	101.53725	103.78475	131.81150	107.87775	111.24925	104.01875	109.5020	116.04450	105.59650	101.32300	106.24775	115.75200	92.19875	104.26875	107.14425	102.21425	111.41325	123.85425	101.98475	108.94725	103.91725	106.69575	121.15200	115.34075	107.32600	105.28125	113.4085	118.31375	105.89775	103.69375	126.95700	111.03375	104.36725	108.66475	109.75675
2	2012	104.07175	110.63300	170.32750	120.65275	129.16900	117.80575	115.1725	138.57875	110.88150	102.74725	109.49900	147.46800	83.28000	119.27800	112.45725	97.90175	125.17300	148.83975	105.11225	113.70325	106.71575	107.81950	142.38200	133.33875	113.67750	107.55275	137.1715	145.01325	107.70150	110.10950	150.74725	120.93250	116.90500	113.88775	120.46675
3	2013	116.27650	130.56400	191.61625	127.15625	136.18075	137.26350	120.3040	150.94075	123.46825	106.19475	112.27775	184.80025	92.26350	123.59450	134.52225	92.37850	153.48125	158.91900	113.93700	122.01075	116.59175	108.56500	171.24675	157.54900	120.54600	118.16900	180.6850	190.80675	110.85300	123.29000	181.36625	137.46225	138.64800	123.33150	138.68850
4	2014	133.69175	154.13400	220.14950	143.16750	165.08475	144.57075	141.1915	188.93475	140.00225	111.70625	121.78200	230.17750	106.67700	129.58350	162.81525	95.91100	181.68300	183.42750	128.40525	121.79475	135.62400	115.74175	207.52175	180.00800	132.23875	131.47725	223.2990	249.28800	120.81950	142.89900	209.12425	158.86300	167.51250	138.88250	162.42250

	Year	job_creation_Auckland	job_creation_Bay of Plenty	job_creation_Canterbury	job_creation_Gisborne	job_creation_Hawke's Bay	job_creation_Manawatu-Wanganui	job_creation_Otago	job_creation_Taranaki	job_creation_Tasman, Nelson, Marlborough, West Coast	job_creation_Waikato	job_creation_Wellington	job_destruction_Auckland	job_destruction_Bay of Plenty	job_destruction_Canterbury	job_destruction_Gisborne	job_destruction_Hawke's Bay	job_destruction_Manawatu-Wanganui	job_destruction_Otago	job_destruction_Taranaki	job_destruction_Tasman, Nelson, Marlborough, West Coast	job_destruction_Waikato	job_destruction_Wellington	Not in Labour Force	Working Age Population	Labour Force Participation Rate	Unemployment Rate	Employment Rate	Total Labour Force	AVI_Auckland	AVI_Bay of Plenty	AVI_Canterbury	AVI_Gisborne Hawke's Bay	AVI_Marlborough/NelsonTasman/West Coast	AVI_Manawatu/Wanganui-Taranaki	AVI_Northland	AVI_Otago Southland	AVI_Waikato	AVI_Wellington	AVI_ids_Accounting	AVI_ids_Construction	AVI_ids_Education	AVI_ids_Health	AVI_ids_Hospitalty	AVI_ids_IT	AVI_ids_Manufacturing	AVI_ids_Primary	AVI_ids_Sales	AVI_ids_Other	AVI_ocp_Managers	AVI_ocp_Professionals	AVI_ocp_Tech & Trades	AVI_ocp_Community & Personal Services	AVI_ocp_Clerical & Administration	AVI_ocp_Sales	AVI_ocp_Machinery Drivers	AVI_ocp_Labourers	AVI_ocp_highly skilled	AVI_ocp_skilled	AVI_ocp_semi-skilled	AVI_ocp_low skilled	AVI_ocp_unskilled	AVI_ocp_Skilled	AVI_ocp_Unskilled	median_wage_15-19	median_wage_20-24	median_wage_25-29	median_wage_30-34	median_wage_35-39	median_wage_40-44	median_wage_45-49	median_wage_50-54	median_wage_55-59	median_wage_60-64	median_wage_65	median_wage_Total All Ages	GDP_Northland	GDP_Auckland	GDP_Waikato	GDP_Bay of Plenty	GDP_Gisborne	GDP_Hawke's Bay	GDP_Taranaki	GDP_Manawatu-Whanganui	GDP_Wellington	GDP_West Coast	GDP_Canterbury	GDP_Otago	GDP_Southland	GDP_Marlborough	GDP_Tasman/Nelson	GDP_Total North Island	GDP_Total South Island	GDP_New Zealand	GDP_Agriculture	GDP_Forestry, Fishing, and Mining	GDP_Forestry, Fishing, Mining, Electricity, Gas, Water and Waste Services	GDP_Primary Manufacturing	GDP_Other Manufacturing	GDP_Manufacturing	GDP_Electricity, Gas, Water, and Waste services	GDP_Construction	GDP_Wholesale Trade	GDP_Retail Trade	GDP_Accommodation and Food Services	GDP_Accommodation	GDP_Food and beverage services	GDP_Transport, Postal and Warehousing	GDP_Information Media, Telecommunications and Other Services	GDP_Financial and Insurance Services	GDP_Rental, Hiring and Real Estate Services	GDP_Owner-Occupied Property Operation	GDP_Professional, Scientific, and Technical Services	GDP_Administrative and Support Services	GDP_Public Administration and Safety	GDP_Education and Training	GDP_Health Care and Social Assistance	GDP_Total All Industries
0	2010	18130	1580	3320	250	830	840	1240	475	800	2730	4910	15380	1430	3470	195	850	980	1300	515	900	2270	5290	645.7	2844.4	77.3	6.3	72.4	2198.7	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000	100.00000	3060.0	8050.0	10582.5	11865.0	12315.0	12137.5	12065.0	11905.0	11437.5	10515.0	7245.0	10632.5	4543.0	63382.0	15258.0	9409.0	1324.0	5150.0	7665.0	7544.0	25113.0	1351.0	22229.0	7894.0	4168.0	1794.0	3296.0	139388.0	40731.0	180119.0	8654	6651	12720	13001	7925	20926	6069	10464	9869	8292	3789	1226	2563	7929	12490	11119	13413	12192	14735	3633	8732	9204	11958	180119
1	2011	17310	1600	4100	190	710	810	1140	480	850	2220	5310	14540	1370	3730	190	690	890	1110	490	760	1920	5120	655.8	2866.7	77.1	6.4	72.2	2211.0	101.53725	103.78475	131.81150	107.87775	111.24925	104.01875	109.50200	116.04450	105.59650	101.32300	106.24775	115.75200	92.19875	104.26875	107.14425	102.21425	111.41325	123.85425	101.98475	108.94725	103.91725	106.69575	121.15200	115.34075	107.32600	105.28125	113.40850	118.31375	105.89775	103.69375	126.95700	111.03375	104.36725	108.66475	109.75675	3152.5	8162.5	10835.0	12155.0	12712.5	12565.0	12462.5	12290.0	11845.0	10967.5	7752.5	10972.5	4842.0	65759.0	16075.0	9947.0	1394.0	5447.0	7977.0	7888.0	25501.0	1427.0	23219.0	8171.0	4498.0	1813.0	3446.0	144830.0	42574.0	187404.0	10643	6938	13291	13860	8191	22051	6353	10470	10081	8469	3857	1248	2609	8758	12421	9975	13648	13484	15529	3959	8835	9595	12337	187404
2	2012	17260	1560	4580	195	820	1040	1230	510	800	2710	5880	14410	1510	3710	160	920	940	1200	450	790	2290	5080	652.5	2876.3	77.3	6.3	72.4	2223.8	104.07175	110.63300	170.32750	120.65275	129.16900	117.80575	115.17250	138.57875	110.88150	102.74725	109.49900	147.46800	83.28000	119.27800	112.45725	97.90175	125.17300	148.83975	105.11225	113.70325	106.71575	107.81950	142.38200	133.33875	113.67750	107.55275	137.17150	145.01325	107.70150	110.10950	150.74725	120.93250	116.90500	113.88775	120.46675	3257.5	8370.0	11112.5	12452.5	13102.5	13020.0	12925.0	12735.0	12280.0	11435.0	8245.0	11335.0	4922.0	68978.0	17102.0	10321.0	1432.0	5575.0	7896.0	7997.0	26724.0	1517.0	24316.0	8402.0	4599.0	1919.0	3503.0	150947.0	44256.0	195203.0	10622	6772	13371	15298	8017	23315	6600	10804	10526	8878	3940	1245	2696	9331	12960	10625	14757	14344	15869	4172	9041	9985	12665	195203
3	2013	18320	1800	4360	305	790	770	1290	660	830	2110	5820	13340	1470	3770	245	710	780	1070	480	760	1950	4720	666.9	2878.8	76.8	6.6	71.8	2211.9	116.27650	130.56400	191.61625	127.15625	136.18075	137.26350	120.30400	150.94075	123.46825	106.19475	112.27775	184.80025	92.26350	123.59450	134.52225	92.37850	153.48125	158.91900	113.93700	122.01075	116.59175	108.56500	171.24675	157.54900	120.54600	118.16900	180.68500	190.80675	110.85300	123.29000	181.36625	137.46225	138.64800	123.33150	138.68850	3290.0	8555.0	11340.0	12705.0	13407.5	13420.0	13267.5	13065.0	12647.5	11850.0	8620.0	11617.5	4899.0	71351.0	16725.0	10490.0	1427.0	5730.0	7967.0	7999.0	27149.0	1449.0	25371.0	8526.0	4432.0	2001.0	3581.0	153739.0	45360.0	199099.0	9130	6610	13764	15133	7938	23071	7154	11541	10530	9489	4124	1270	2855	9790	13188	10921	15134	15260	16555	4165	9147	10154	13133	199099
4	2014	18870	1580	4710	285	690	860	1380	550	1010	2350	6050	15940	1620	3600	245	720	800	1180	600	690	2400	4680	641.8	2899.4	77.9	6.0	73.2	2257.6	133.69175	154.13400	220.14950	143.16750	165.08475	144.57075	141.19150	188.93475	140.00225	111.70625	121.78200	230.17750	106.67700	129.58350	162.81525	95.91100	181.68300	183.42750	128.40525	121.79475	135.62400	115.74175	207.52175	180.00800	132.23875	131.47725	223.29900	249.28800	120.81950	142.89900	209.12425	158.86300	167.51250	138.88250	162.42250	3392.5	8820.0	11590.0	13025.0	13767.5	13877.5	13655.0	13475.0	13017.5	12245.0	9032.5	11925.0	5363.0	75444.0	18690.0	11030.0	1474.0	6044.0	8508.0	8558.0	28348.0	1548.0	28198.0	9224.0	5075.0	2224.0	3873.0	163457.0	50143.0	213600.0	13111	6842	14266	15619	8209	23828	7424	12398	11592	9987	4368	1336	3034	10356	13731	12265	16128	16147	17763	4283	9399	10503	13473	213600
5	2015	18550	1920	4540	180	780	720	1340	485	770	2440	5750	16200	1390	3960	205	800	780	1240	550	970	2510	4920	625.3	2953.7	78.8	5.6	74.4	2328.3	145.30325	172.99950	209.96075	155.77475	165.05950	143.59000	150.65925	198.53075	137.80175	107.15200	132.47975	241.83900	129.02475	136.66400	171.36475	84.66750	188.76625	170.08400	129.65700	125.58400	142.62450	117.33000	215.30150	185.26900	139.21500	135.11000	226.86450	258.14750	122.26300	153.56575	220.05500	163.96100	173.75725	142.87150	167.60600	3470.0	9025.0	11745.0	13300.0	14057.5	14255.0	14037.5	13852.5	13335.0	12595.0	9360.0	12192.5	5555.0	81076.0	18754.0	11291.0	1541.0	6176.0	8329.0	8681.0	29588.0	1479.0	29434.0	9427.0	4841.0	2338.0	3996.0	170990.0	51516.0	222506.0	8240	6936	14531	18113	8753	26866	7595	13833	12486	10491	4763	1364	3420	11424	14452	13514	16526	17148	18570	4556	9824	10998	14263	222506
6	2016	18440	2120	5510	285	730	1000	1560	585	830	2820	5990	14920	2220	4270	285	700	800	1270	600	880	2130	5350	646.8	3022.5	78.6	5.6	74.2	2375.8	165.82600	216.45450	201.01200	185.86800	197.03000	155.69875	170.62350	227.02200	159.73250	118.36025	147.28575	278.17775	139.57950	144.00600	196.75375	84.84350	219.53000	196.57500	141.57025	154.53600	158.96325	124.94600	250.19975	201.40250	156.16900	144.60050	269.36675	312.98700	131.72300	172.76600	252.50325	181.38500	202.33150	157.08750	188.63650	3570.0	9267.5	11977.5	13605.0	14405.0	14702.5	14470.0	14267.5	13745.0	12967.5	9682.5	12505.0	5994.0	88139.0	19413.0	12287.0	1638.0	6444.0	7221.0	8944.0	30654.0	1380.0	30338.0	10057.0	4693.0	2440.0	4216.0	180735.0	53124.0	233859.0	7691	6107	13779	19703	9105	28808	7673	15170	12856	11083	5327	1560	3745	12430	15012	13962	17919	18106	19932	4889	10322	11431	15164	233859
7	2017	22050	2090	5140	265	950	1120	1640	655	910	2640	8000	15250	1710	4870	260	710	860	1200	590	630	2260	6650	608.7	3103.3	80.4	5.3	76.1	2494.7	175.23000	243.52650	211.83100	214.93775	250.45875	179.49775	211.60125	282.45575	195.68175	127.82375	148.99275	310.85125	149.96350	158.51150	214.95475	77.32675	279.99425	241.28300	147.70400	228.61125	170.49775	130.92325	269.98625	214.66600	163.59300	159.66025	348.40925	390.85125	139.53325	182.87725	272.59550	207.35825	232.79000	166.67750	216.22275	3822.5	9607.5	12285.0	13912.5	14750.0	15095.0	14952.5	14665.0	14147.5	13327.5	9995.0	12832.5	6428.0	93624.0	20709.0	13820.0	1707.0	7011.0	7279.0	9358.0	32240.0	1450.0	31189.0	10745.0	5122.0	2604.0	4492.0	192176.0	55602.0	247778.0	11108	6438	14320	17562	9820	27381	7882	16763	12843	12294	5947	1830	4213	12263	15447	14487	19690	19297	21780	5330	10902	11924	15905	247778
8	2018	22660	2360	6720	290	860	970	1720	590	880	2940	7220	17380	2060	5530	217	730	1150	1560	485	770	2680	6270	600.8	3165.2	81.0	4.8	77.1	2564.3	178.72850	283.24475	211.24675	258.77075	284.16925	210.15675	243.12150	327.30875	224.37100	139.30525	156.54725	319.92250	155.55325	189.20975	231.89250	86.00700	302.97500	271.96825	152.39075	249.15500	177.33800	140.40925	275.51950	234.19450	171.59100	166.48125	376.26800	453.76300	150.22225	187.26825	277.11225	222.08300	257.69600	175.38925	234.23950	4052.5	10072.5	12815.0	14397.5	15257.5	15665.0	15582.5	15247.5	14727.5	13915.0	10507.5	13357.5	6970.0	99794.0	22583.0	15106.0	1844.0	7567.0	8129.0	10123.0	33610.0	1632.0	33555.0	11754.0	5609.0	2798.0	4835.0	205727.0	60184.0	265911.0	12610	7422	15426	19546	10092	29638	8004	19009	13977	12896	6247	1922	4440	12909	15889	16262	20538	20772	23382	5728	11531	12275	16708	265911
9	2019	19170	2290	5700	270	900	980	1820	725	1010	3260	6840	20200	2130	4860	225	920	980	1630	690	920	2600	6690	608.7	3219.5	81.1	4.5	77.5	2610.9	170.89575	290.04425	197.05425	286.09400	286.96150	212.75400	235.37500	340.89400	224.38775	148.06575	152.72900	310.46125	152.83000	194.33425	226.29225	91.44775	286.35175	268.00600	147.67325	282.87050	173.58700	141.81725	267.49075	244.36825	169.20850	154.99575	349.33125	473.02500	150.12700	187.57650	273.23250	209.39475	263.28000	176.35950	226.13875	4252.5	10460.0	13295.0	14860.0	15780.0	16160.0	16220.0	15822.5	15237.5	14417.5	11020.0	13852.5	7238.0	105433.0	24349.0	16322.0	1999.0	7886.0	8245.0	10744.0	34849.0	1685.0	35066.0	12484.0	5932.0	2966.0	5162.0	217065.0	63295.0	280360.0	12655	7652	16141	19888	10567	30455	8489	20314	14394	13503	6471	2105	4609	13609	16734	17161	21988	22127	25041	6116	12279	13099	18030	280360
10	2020	20070	1950	5130	250	940	990	1470	680	1090	2800	6460	17190	1740	4740	175	750	1010	1410	570	1000	2400	5170	622.2	3272.4	81.0	4.3	77.5	2650.3	146.18475	271.09825	167.69850	316.91225	272.20025	218.50475	242.59325	294.45425	207.24825	139.34550	134.22625	288.20650	141.80250	193.32050	193.00775	77.95150	267.99125	261.99975	123.96100	272.39275	156.77425	128.82050	247.31050	216.38300	132.52175	130.04775	342.76125	454.21950	136.42800	165.02750	256.37650	181.03125	236.54725	154.66700	199.12575	4595.0	10627.5	13565.0	15062.5	15942.5	16417.5	16535.0	16147.5	15552.5	14747.5	11495.0	14167.5	7712.0	110312.0	25993.0	17283.0	2056.0	8397.0	8483.0	11344.0	37561.0	1725.0	37099.0	13097.0	6093.0	3135.0	5487.0	229139.0	66638.0	295777.0	13866	7383	16375	20524	10733	31257	8992	22400	14558	13983	6823	2140	4875	13817	17359	17594	23654	23810	27100	6289	13457	13795	19447	295777
11	2021	22980	3300	6180	270	1390	1090	1780	790	1160	3800	7750	16450	2340	4950	185	770	930	1390	660	860	2800	5470	643.7	3318.6	80.6	4.9	76.6	2674.9	189.51575	392.75500	248.80475	451.37950	381.41450	306.77775	344.60875	396.52100	291.07275	195.25350	177.00750	389.31900	197.62975	294.09700	233.62625	115.64900	401.49900	338.09400	157.81250	369.92700	191.84925	180.05150	329.80450	282.02625	194.41750	180.38150	487.17575	639.70600	183.62100	209.55175	336.20350	257.89600	337.49750	211.00625	282.83275	4875.0	11410.0	14522.5	16010.0	16915.0	17427.5	17552.5	17115.0	16440.0	15597.5	12175.0	15062.5	7804.0	113290.0	26954.0	18012.0	2256.0	8878.0	8077.0	12115.0	37606.0	1784.0	37011.0	12860.0	6180.0	3197.0	5582.0	234991.0	66613.0	301604.0	14319	6645	15200	19432	11376	30808	8555	23294	15958	15235	6002	1557	4255	11724	17244	18121	24686	25464	28022	5633	14219	14507	21356	301604
12	2022	23740	2460	5800	265	940	1130	1870	620	1160	3500	6770	17440	2070	4100	345	770	890	1510	570	1110	2720	5670	603.1	3310.2	81.8	3.6	78.8	2707.1	200.32850	429.89125	286.85100	459.61800	394.09675	342.01750	402.06400	457.42375	302.15075	192.75275	188.98575	391.05925	213.92500	333.00550	338.50825	107.83000	437.89625	342.50450	173.08300	368.58675	188.49375	186.20775	348.89025	362.15575	208.88800	201.23075	492.31925	695.99400	185.33725	241.53550	342.63600	281.00425	386.71325	217.79625	314.24425	5285.0	12522.5	15717.5	17320.0	18235.0	18725.0	18897.5	18440.0	17642.5	16700.0	13062.5	16185.0	8684.0	124270.0	29378.0	19527.0	2318.0	9773.0	8911.0	13110.0	40777.0	1798.0	40380.0	14016.0	7144.0	3283.0	6038.0	256748.0	72659.0	329407.0	16373	6805	16463	19567	12030	31597	9658	24320	18992	16985	6851	1743	4896	13124	18604	20252	26033	27240	31774	6671	15185	15489	23665	329407

		AVI_Auckland
GDP_Auckland_Grade	AVI Auckland Classified
E	Low	101.869667
D	Low	131.757156
C	High	170.528000
B	High	174.812134
A	High	194.922119
A	Low	146.184753

		AVI_Auckland
	AVI Auckland Classified	High	Low
Unemployment Rate Classified	GDP_Auckland_Grade
High	E	NaN	101.869667
High	D	NaN	124.984131
Low	D	NaN	145.303253
	C	170.528000	NaN
	B	174.812134	NaN
	A	194.922119	146.184753

New Zealand's Job Landscape: Industry Contribution to the Country and Current Job Opportunities in the Technology Industry¶

Introduction¶

Datasets used:¶

Dataset sources:¶

Research Questions¶

Executive Summary¶

Data Acquisition&Wraggling¶

Data Integration¶

Analysis¶

1. Data Acquisition&Wraggling¶

1.1 Dynamic datasets¶

1.1.1 NZ Industry Contributions to GDP and Employment¶

1.1.2 Job profiles datasets¶

1.2 Static datasets¶

1.2.1 Job market¶

1.2.1.1 Job online dataset¶

1.2.1.2 Regional Employment Data¶

1.2.1.3 Labour Force Status¶

1.2.1.4 Median wage¶

1.2.2 GDP datasets¶

1.2.2.1 GPD region¶

1.2.2.2 GPD industry¶

2.Data Integration¶

2.1 Job market datasets¶

2.1.1 Online job datasets¶

2.1.2 Region data¶

2.1.3 Median Wage¶

2.2 GDP datasets¶

2.2.1 GDP region¶

2.2.2 GDP industry¶

2.3 Merge datasets¶

2.4 Big Data Processing Optimization¶

2.4.1 Convert to Dask DataFrame¶

2.4.2 Changing data types¶

2.4.3 Store data in HDF5 format¶

3. Data Analysis¶

3.1 Discuss the overall GDP changes in New Zealand from 2010 to 2022. What are the top three industrial contributions?¶

3.1.1 GDP Distribution in North Island, South Island and New Zealand from 2010 to 2022¶

3.1.2 GDP Distribution by Industry in New Zealand from 2010 to 2022¶

3.1.3 Finding the Top 3 Contribution Industries to New Zealand GDP for 2022-2023¶

3.2 Does the Industry that Contributes the Most GDP Bring the Same Proportion of Job Opportunities?¶

3.2.1 Adding Employment Job Numbers Variable and Analyzing Their Relationship to GDP Proportion¶

3.3 Based on the Occupation Listed on Careers.NZ. What's the Job Opportunities in 6 Main Industries?¶

3.3.1 Job Opportunities by 6 Main Industries in New Zealand (Lastest DATA)¶

3.3.2 Job Opportunities by 6 Main Industries in New Zealand (Lastest DATA) - Accumulated¶

★ Note: The above source listed in each graph shows various methods we used to collect data. From below graph, the source of each table's data will not be specifically indicated.¶

3.4 As the Largest City in New Zealand and a Major Economic Hub, is Auckland the Best in Terms of All Vacancy Indices (AVIs) and GDP from 2010 to 2022?¶

3.4.1 All Vacancy Indices (AVIs) by Region from 2010-2022¶

3.4.2 GDP Contribution by Region from 2010-2022¶

3.5 How Does Unemployment Rate in New Zealand Relate to Auckland's AVI and GDP?¶

3.5.1 Create the Classified Column for Unemployment Rate and AVI Auckland by Median.¶

3.5.2 Create the Classified Column for GDP Auckland by 5 Grades.¶

3.5.3 Display the Correlation of Overall Unemployment Rate with Auckland's AVI and GDP by Pivot Table.¶

3.5.4 Visualize the Correlation of Overall Unemployment Rate with Auckland's AVI and GDP.¶

3.6 Does the Job Creation in Auckland from 1999 to 2022 Remain Positive, Making Auckland the City with the Most Economic Contribution?¶

3.6.1 Build a pivot table that classifies job creation and job destruction in Auckland from 1999 to 2022,¶

3.6.2 Visualize the pivot table.¶

3.7 What are the Employment Prospects and Highest Salary Ranges for the Manufacturing and Technology Industries, as well as for Data Analyst Positions?¶

3.7.1 Group by the Manufacturing and technology industry with Good Job Opportunities.¶

3.7.2 Transfer the earnings column from text to number.¶

3.7.3 Visualize the maximum yearly salary by occupation and training years in the manufacturing and technology industries.¶

Summary¶

Conclusion¶